JP4730137B2 - Mobile body safety evaluation method and mobile body safety evaluation apparatus - Google Patents

Mobile body safety evaluation method and mobile body safety evaluation apparatus Download PDF

Info

Publication number
JP4730137B2
JP4730137B2 JP2006055442A JP2006055442A JP4730137B2 JP 4730137 B2 JP4730137 B2 JP 4730137B2 JP 2006055442 A JP2006055442 A JP 2006055442A JP 2006055442 A JP2006055442 A JP 2006055442A JP 4730137 B2 JP4730137 B2 JP 4730137B2
Authority
JP
Japan
Prior art keywords
moving body
specific
moving
trajectory
step
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
JP2006055442A
Other languages
Japanese (ja)
Other versions
JP2007233765A (en
Inventor
敏樹 金道
和昭 麻生
Original Assignee
トヨタ自動車株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by トヨタ自動車株式会社 filed Critical トヨタ自動車株式会社
Priority to JP2006055442A priority Critical patent/JP4730137B2/en
Publication of JP2007233765A publication Critical patent/JP2007233765A/en
Application granted granted Critical
Publication of JP4730137B2 publication Critical patent/JP4730137B2/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Description

  The present invention predicts the course of each moving body based on the position and internal state of a plurality of moving bodies such as automobiles, and calculates the degree of interference between the courses of the moving body using this prediction result. The present invention relates to a mobile body safety evaluation method and a mobile body safety evaluation apparatus for evaluating the safety of a specific mobile body such as a car.

  In recent years, various attempts have been made to realize automatic driving of a moving body such as a four-wheeled vehicle. In order to realize automatic driving of moving objects, it is possible to accurately detect moving objects such as vehicles (automobiles, motorcycles, bicycles, etc.) and pedestrians in the surrounding area, and to detect danger during traveling based on the detection results. Avoidance is important. Among these, object detection techniques using various sensors and various radars are known as techniques for accurately detecting surrounding moving objects.

  On the other hand, as a technique for avoiding danger during traveling, in a system composed of a plurality of moving bodies and the own vehicle, information on the position and speed of the own vehicle and positions of a plurality of moving bodies other than the own vehicle And the speed information are used to generate the path of each moving body including the vehicle and predict the possibility that any two of the moving bodies that make up the system will collide. (For example, see Non-Patent Document 1). This technology predicts and outputs the course that can be taken by all the mobile objects that make up the system by the operation sequence of the same framework using the probability concept. Then, based on the obtained prediction result, a route that realizes the safest situation for the entire system including the vehicle is obtained and output.

A. Broadhurst, S. Baker, and T. Kanade, "Monte Carlo Road Safety Reasoning", IEEE Intelligent Vehicle Symposium (IV2005), IEEE, (June 2005)

  However, the technique disclosed in Non-Patent Document 1 mainly focuses on predicting a route that is safe for all the mobile bodies constituting the system. It has not been determined whether or not the safety for a predetermined moving body (for example, the own vehicle) is sufficiently ensured.

  This point will be described more specifically. In an actual road situation, a driver or pedestrian of another vehicle may cause a misunderstanding of the road situation, and may exhibit an undesirable behavior for the surrounding moving body including the own vehicle without the user being aware of it. On the other hand, in Non-Patent Document 1 described above, since it is implicitly assumed that all mobile objects exhibit behavior giving priority to safety, a specific mobile object (for example, a specific other vehicle) It has been unclear whether sufficient safety can be ensured even in situations that may occur in reality, as in the case where a behavior undesirable for a predetermined surrounding mobile body (for example, the own vehicle) is exhibited.

  The present invention has been made in view of the above, and by making it possible to recognize the degree of danger that a specific moving body is allowed to move, it is safe even in a situation that may occur in reality. It is an object of the present invention to provide a mobile body safety evaluation method and a mobile body safety evaluation apparatus that can ensure safety.

  In order to solve the above-described problems and achieve the object, the mobile body safety evaluation method of the invention according to claim 1 stores at least the positions of a plurality of mobile bodies and the internal state including the speed of each mobile body. A moving body safety evaluation method for evaluating the safety of a moving path of a specific moving body included in the plurality of moving bodies with respect to a predetermined moving body other than the specific moving body using storage means, The position and the internal state of the plurality of moving bodies are read from the storage means, and based on the read position and internal state of the moving body, the change in the position that each of the plurality of moving bodies can take with the passage of time is determined over time. And a trajectory generation step generated as a trajectory in space-time composed of space, and a probabilistic prediction of the paths of the plurality of moving objects by using the trajectory generated in the trajectory generation step Based on the prediction step stored in the storage means and the result predicted in the prediction step and stored in the storage means, the predetermined moving body takes each path that the specific moving body can take. An interference degree calculating step for calculating an interference degree quantitatively indicating the degree of interference with the obtained route and storing the interference degree in the storage means; and an actual movement position of the specific moving body is cumulatively accumulated at predetermined time intervals. And an actual movement path recognition step for recognizing the actual movement path of the specific moving body retrospectively in space and time, and the actual movement path recognized in the paths that the specific moving body can take A similar route search step for searching for a route that is most similar to, and extracting the degree of interference calculated for the searched similar route and stored in the storage means as a safety evaluation value of the specific moving body; Have It is characterized in.

  The mobile body safety evaluation method of the invention according to claim 2 is included in the plurality of mobile bodies using storage means for storing at least the positions of the mobile bodies and the internal state including the speed of each mobile body. A moving body safety evaluation method for evaluating the safety of a moving path of a specific moving body with respect to a predetermined moving body other than the specific moving body, wherein the storage means stores the position and internal state of the predetermined moving body Based on the position and internal state of the predetermined moving body that is read from, the position change that the predetermined moving body can take over time is generated as a trajectory in time and space that is composed of time and space A trajectory generating step, a predicting step of performing probabilistic prediction of the course of the predetermined moving body by using the trajectory generated in the trajectory generating step, and storing the path in the storage unit; An actual movement path recognition step for accumulating the actual movement position of a specific moving body at predetermined time intervals and recognizing the actual movement path of the specific moving body in time and space; and the prediction step The degree of interference that quantitatively indicates the degree of interference of the actual moving path of the recognized moving body with respect to the path that can be taken by the predetermined moving body based on the result predicted and stored in the storage means And a degree of interference calculation step of calculating as a safety evaluation value of the specific moving body.

  In the mobile object safety evaluation method according to a third aspect of the present invention, in the above invention, the trajectory generation step includes an operation selection step of selecting an operation for the object from a plurality of operations, and an operation selected in the operation selection step. An object operation step that operates for a predetermined time, and a position and an internal state of the object after operating the selected operation in the object operation step are a control condition related to the control of the object and a movement condition related to a movable region of the object. A determination step of determining whether or not the condition is satisfied, and a series of processing from the operation selection step to the determination step is repeatedly performed until a locus generation time for generating a locus is reached.

  In the mobile object safety evaluation method according to a fourth aspect of the present invention, in the above invention, the operation selection step selects an operation according to an operation selection probability given to each of the plurality of operations, and the determination step determines As a result, when the position and the internal state of the object satisfy the control condition and the movement condition, the time is advanced and the process returns to the operation selection step.

  According to a fifth aspect of the present invention, in the mobile object safety evaluation method according to the present invention, the operation selection probability is defined using a random number.

  The mobile body safety evaluation method of the invention according to claim 6 is characterized in that, in the above invention, the number of trajectories to be generated in the trajectory generation step is predetermined.

  According to a seventh aspect of the present invention, there is provided the mobile body safety evaluation method according to the above invention, wherein the predetermined mobile body is a host vehicle, and the specific mobile body is present around the host vehicle. It is a specific other vehicle.

  According to an eighth aspect of the present invention, there is provided the mobile body safety evaluation device for evaluating the safety of a specific mobile body included in the plurality of mobile bodies with respect to a predetermined mobile body other than the specific mobile body. A body safety evaluation device that stores at least the positions of a plurality of moving bodies and internal states including the speed of each moving body, and reads the positions and internal states of the plurality of moving bodies from the storage means. Based on the read position and internal state of the moving body, a change in position that each of the plurality of moving bodies can take as time elapses is generated as a trajectory on time and space composed of time and space. A trajectory generating means, a predicting means for performing probabilistic prediction of the course of the plurality of moving bodies by using the trajectory generated by the trajectory generating means, and storing the trajectory in the storage means; and Based on the results measured and stored in the storage means, the degree of interference that quantitatively indicates the degree of interference with the path that can be taken by the predetermined moving body is calculated for each course that can be taken by the specific moving body. Interference degree calculating means stored in the storage means, and the actual moving position of the specific moving body is cumulatively stored at a predetermined time interval, and the actual moving path of the specific moving body is expressed in a time-space manner. The actual movement route recognition means that recognizes the above-mentioned retrospectively and the route that is most similar to the recognized actual movement route among the routes that can be taken by the specific moving body, and the searched similar route And a similar route search means for extracting the degree of interference calculated and stored in the storage means as a safety evaluation value of the specific moving body.

  According to a ninth aspect of the present invention, there is provided the mobile body safety evaluation apparatus according to the present invention, wherein the mobile body safety evaluation apparatus includes a mobile body that evaluates the safety of a specific mobile body included in the plurality of mobile bodies against a predetermined mobile body other than the specific mobile body. A body safety evaluation apparatus, which stores at least the position of a plurality of moving bodies and an internal state including the speed of each moving body, and reads the position and the internal state of the predetermined moving body from the storage means Based on the read position and internal state of the predetermined moving body, a trajectory that generates a change in position that the predetermined moving body can take with time as a trajectory on time and space that is composed of time and space A generating unit, a predicting unit that uses the trajectory generated by the trajectory generating unit to make a probabilistic prediction of the course of the predetermined moving body, and stores it in the storage unit; The moving position of the specific moving body is cumulatively stored at a predetermined time interval and the actual moving path of the specific moving body is recognized retrospectively in space and time, and the storage is predicted by the predicting means and stored in the memory. Based on the result stored in the means, an interference degree quantitatively indicating the degree of interference of the recognized actual moving path of the specific moving body with the path that the predetermined moving body can take is the specific moving body. And an interference degree calculating means for calculating the safety evaluation value.

  The mobile body safety evaluation apparatus according to a tenth aspect of the present invention is the mobile body safety evaluation device according to the above invention, wherein the trajectory generation unit includes an operation selection unit that selects an operation for the object from a plurality of operations, and an operation selected by the operation selection unit. An object operating means that operates for a predetermined time, and a position and an internal state of the object after the selected operation is operated by the object operating means are a control condition relating to the control of the object and a moving condition relating to a movable area of the object. A determination unit that determines whether or not the condition is satisfied, and a series of processes from the operation selection process by the operation selection unit to the determination process by the determination unit are repeatedly performed until a trajectory generation time for generating a trajectory is reached. It is characterized by.

  In the mobile body safety evaluation apparatus according to an eleventh aspect of the present invention, in the above invention, the operation selection unit selects an operation according to an operation selection probability given to each of the plurality of operations, and the determination unit determines the operation. As a result, when the position and the internal state of the object satisfy the control condition and the movement condition, the operation selection process by the operation selection unit is returned to advance time.

  The mobile body safety evaluation apparatus according to a twelfth aspect of the present invention is characterized in that, in the above invention, the operation selection probability is defined using a random number.

  According to a thirteenth aspect of the present invention, there is provided the mobile body safety evaluation device according to the above invention, wherein the number of trajectories to be generated by the trajectory generating means is predetermined.

  The mobile body safety evaluation device according to a fourteenth aspect of the present invention is the mobile device safety evaluation device according to the above invention, wherein the predetermined mobile body is a vehicle on which the evaluation device is mounted, and the specific mobile body is around the vehicle. It is a specific other vehicle that exists in and is a target.

  According to the mobile body safety evaluation method and the mobile body safety evaluation apparatus according to the present invention, the positions and internal states of a plurality of mobile bodies are read from the storage means, and a plurality of positions are determined based on the read positions and internal states of the mobile bodies. A change in the position that each of the mobile objects can take over time is generated as a trajectory in time and space that is composed of time and space. Predicting and storing in the storage means, and based on the predicted result stored in the storage means, for each course that can be taken by a specific mobile body, the degree of interference with the course that a predetermined mobile body can take The degree of interference shown quantitatively is calculated and stored in the storage means, and the actual moving position of the specific moving body is cumulatively stored at a predetermined time interval, so that the actual moving path of the specific moving body is determined. Go back in time and space Interference that is recognized and searched for a route that is most similar to the recognized actual moving route among the routes that can be taken by a specific moving body, and that is calculated for the searched similar route and stored in the storage means Since the degree of safety is extracted as the safety evaluation value of a specific mobile object, the specific mobile object is actually used in the environment of the movement path that is expected to be taken by both the specific mobile object and the predetermined mobile object. It is possible to recognize the degree of danger that the specific moving body has allowed to move by collating and evaluating the degree of the risk that the movement path was taken. By recognizing the behavior of the body, there is an effect that it is possible to ensure safety even in a situation that can occur in reality.

  Further, according to another mobile body safety evaluation method and mobile body safety evaluation apparatus according to the present invention, the position and internal state of a predetermined mobile body are read from the storage means, and the read position and internal position of the predetermined mobile body are read out. Based on the state, a change in the position that the predetermined moving body can take as time elapses is generated as a trajectory in time and space composed of time and space, and by using the generated trajectory, the predetermined moving body Probabilistic prediction of the course is stored in the storage means, the actual movement position of the specific moving body is cumulatively stored at a predetermined time interval, and the actual movement path of the specific moving body is stored in time and space. Based on the result of the recognition that is recognized retroactively and stored in the storage means, the degree of interference of the actual movement path of the recognized specific movement body with respect to the path that the predetermined movement body can take is quantitatively determined. Indicating the degree of interference Since it is calculated as the safety evaluation value of a fixed mobile body, the travel path of what risk the specific mobile body actually has in the environment of the travel path that is expected to be taken by the predetermined mobile body It is possible to recognize the degree of danger that the specific moving body has moved by allowing the movement of the specific moving body to be recognized. There is an effect that the safety can be ensured even under the obtained conditions.

  Hereinafter, embodiments of a mobile body safety evaluation method and a mobile body safety evaluation apparatus according to the present invention will be described in detail with reference to the drawings. Note that the present invention is not limited to the embodiments, and various modified embodiments are possible without departing from the spirit of the present invention.

(Embodiment 1)
FIG. 1 is a schematic block diagram showing a functional configuration of a mobile body safety evaluation apparatus according to Embodiment 1 of the present invention. This mobile body safety evaluation device 1 is mounted on a mobile body (own vehicle) such as a four-wheeled vehicle, detects a mobile body such as another vehicle existing in a predetermined range around the own vehicle, and in these mobile bodies The course of the specific other vehicle (specific moving body) and the own vehicle (predetermined moving body) is predicted, and the degree of interference between the course that the specific other vehicle can take and the course that the own vehicle can take is determined based on the prediction result. While evaluating quantitatively, the actual travel route of the specific other vehicle is recognized retrospectively, and the risk of the specific other vehicle actually taking the travel route from the similar route corresponding to the actual travel route is determined. It is a device to evaluate.

  The mobile body safety evaluation apparatus 1 includes an input unit 2 to which various types of information are input from the outside, a sensor unit 3 that detects the position and internal state of the mobile body that exists in a predetermined range, and a mobile body that exists in the predetermined range. The change in position that the mobile body can take over time based on the result of detection by the sensor unit 3 or the sensor unit 3 that acquires information on the position and internal state of A trajectory generation unit 5 that generates a trajectory in space-time composed of a space, a prediction unit 6 that performs probabilistic prediction of the course of a moving object using the trajectory generated by the trajectory generation unit 5, and a prediction unit 6 shows the degree of interference between the specific other vehicle and the own vehicle based on the prediction result stored in the past own time / temporal environment storage unit 7 for storing the result predicted in step 6 Specific other vehicles that calculate the degree of interference that quantitatively indicates Based on the information acquired by the road interference degree calculation unit 8, the road-specific interference degree storage unit 9 that stores the degree of interference calculated by the specific other vehicle course interference degree calculation unit 8, and the information acquired by the outside environment sensor 4. The specific other vehicle separating unit 10 that extracts the specific other vehicle from the moving body of the vehicle and the actual position of the specific other vehicle acquired by the outside environment sensor 4 and separated by the specific other vehicle separating unit 10 are accumulated at predetermined time intervals. Specific storage stored in the actual travel route storage unit 11 for recognizing retroactively the actual travel route that the specific other vehicle has passed and the past self-other time and space environment storage unit 7 A route that most closely resembles the actual travel route of the specific other vehicle stored in the actual travel route storage unit 11 among the routes that can be taken by the other vehicle is searched, and is calculated for the similar route, and the interference degree storage unit 9 for each route is calculated. The interference degree stored in the It includes similar other vehicle route searching unit 13 to be output to the output terminal 12 side out, and a storage unit 14 for storing various information including the position and the internal state of the mobile body detected by the sensor unit 3.

  The input unit 2 has a function of inputting various setting information and the like when predicting the course of the moving body, and includes a remote controller, a keyboard (including a touch panel format that allows an input operation on the screen), a pointing device (mouse , Trackpad, etc.). Further, a microphone capable of inputting information by voice may be provided as the input unit 2.

  The sensor unit 3 is realized by using a millimeter wave radar, a laser radar, an image sensor, or the like. The sensor unit 3 includes various sensors such as a speed sensor, an acceleration sensor, a rudder angle sensor, and an angular velocity sensor, and can also detect the movement state of the host vehicle. The vehicle exterior environment sensor 4 is for acquiring information that cannot be acquired by the sensors mounted on the host vehicle, and is provided from, for example, an optical beacon, a radio beacon, or the like in a road-to-vehicle communication system provided on an administrator side managing an expressway. This is realized by using an in-vehicle device such as a VICS-compatible car navigation system that obtains information. Note that the internal state of the moving object detected by the sensor unit 3 or acquired by the outside environment sensor 4 is meaningful for the prediction of the moving object, and is preferably a physical quantity such as the speed, acceleration, angular velocity, acceleration, etc. of the object. is there. For example, a case where the value of a physical quantity such as the speed or angular velocity of a moving body such as the own vehicle is 0 (a state where the object is stopped) is naturally included.

  The trajectory generation unit 5 includes an operation selection unit 51 that selects an operation for a moving body from a plurality of operations, a mobile body operation unit 52 that performs an operation selected by the operation selection unit 51 for a predetermined time, and an operation performed by the mobile body operation unit 52. And a determination unit 53 that determines whether or not the position and internal state of the moving body after satisfying a predetermined condition.

  The storage unit 14 stores the trajectory generated by the trajectory generation unit 5, the operation selected by the operation selection unit 51 of the trajectory generation unit 5, and the like in addition to the detection result of the sensor unit 3. Together with the storage unit 7, the path-specific interference degree storage unit 9 and the actual movement route storage unit 11, a single memory is used. The memory such as the storage unit 14 includes a ROM (Read Only Memory) in which a program for starting a predetermined OS (Operation System), a mobile safety evaluation program according to the first embodiment, and the like, and each process are stored. This is implemented using a RAM (Random Access Memory) that stores the operation parameters, data, and the like. Further, the memory such as the storage unit 14 may be realized by providing an interface on which a computer-readable recording medium can be mounted on the mobile body safety evaluation apparatus 1 and mounting a recording medium corresponding to this interface. it can.

  The trajectory generation unit 5, the prediction unit 6, the specific other vehicle course interference evaluation unit 8, the specific other vehicle separation unit 10, the similar other vehicle course search unit 13 and the storage unit in the mobile body safety evaluation apparatus 1 having the above functional configuration. 7, 9, 11, and 14 are realized by a processor (computer) 15 including a CPU (Central Processing Unit) having calculation and control functions. That is, the CPU included in the mobile body safety evaluation apparatus 1 stores information stored in the memory such as the storage unit 14 and various programs including the above-described object course prediction program and the mobile body safety evaluation program, such as the storage unit 14. The calculation process regarding the mobile body safety evaluation method according to the first embodiment is executed by reading from the memory.

  Next, the mobile body safety evaluation method according to Embodiment 1 of the present invention will be described. FIG. 2 is a flowchart showing an outline of processing of the mobile body safety evaluation method according to the first embodiment. In the following description, it is assumed that all the mobile bodies to be predicted move on a two-dimensional plane. However, the mobile body safety evaluation method according to the first embodiment moves in a three-dimensional space. The present invention is also applicable to control of a moving body that moves and an actuator (robot arm or the like) having an arbitrary degree of freedom.

  First, the sensor unit 3 and the outside environment sensor 4 detect the position and internal state of a moving body within a predetermined range with respect to the own vehicle (predetermined moving body), and store the detected information in the storage unit 14 (step S1). ). Hereinafter, it is assumed that the position of the moving body is a value at the center of the moving body, and the internal state of the moving body is specified by the speed (speed v, direction θ). In this step S1, the internal state of the vehicle is also detected and stored in the storage unit 14 as a matter of course.

Next, the trajectory generation unit 5 generates a trajectory for each moving object by using the detection result input by the sensor unit 3 or the outside environment sensor 4 (step S2). FIG. 3 is a flowchart showing details of the locus generation processing in the locus generator 5. In the figure, the total number of moving bodies (including the own vehicle) detected by the sensor unit 3 and the outside environment sensor 4 is K, and for one moving body O k (1 ≦ k ≦ K, k is a natural number). It is assumed that the operation for generating the locus is performed N k times (in this sense, k and N k are both natural numbers). Further, the time for generating the locus (trajectory generation time) is T (> 0).

First, initialization is performed so that the value of the counter k for identifying the moving object is set to 1, and the value of the counter n indicating the number of times of trajectory generation for the same moving object is set to 1 (step S201). Note that the following description will be described as a process for the mobile O k of general regardless of the vehicle / specific other vehicle.

Next, the trajectory generation unit 5 reads the result detected by the sensor unit 3 or the outside environment sensor 4 from the storage unit 14, and sets the read detection result as an initial state (step S202). Specifically, the time t is set to 0, and the initial position (x k (0), y k (0)) and the initial internal state (v k (0), θ k (0)) are It is assumed that the input information (x k0 , y k0 ) and (v k0 , θ k0 ) from the outside environment sensor 4.

Subsequently, the operation selection unit 51 performs one operation u k (t) to be performed during the subsequent time Δt according to an operation selection probability given in advance to each operation from a plurality of selectable operations. Is selected (step S203). Operation u operation selection probability for selecting the kc p (u kc) is defined by associating the elements with a predetermined random number, for example a set of selectable operations as u k (t) {u kc }. In this sense, a different operation selection probability p (u kc ) may be given for each operation u kc , or an equal probability may be given to all elements of the operation set {u kc }. In the latter case, p (u kc ) = 1 / (total number of selectable operations). The operation selection probability p (u kc ) can be defined as a function that depends on the position and internal state of the vehicle and the surrounding road environment.

In general, the operation u kc is composed of a plurality of elements, the contents of selectable operations depends on the type of mobile O k. For example, when the moving body Ok is a four-wheeled vehicle, the acceleration and angular velocity of the four-wheeled vehicle are determined by the degree of steering and the degree of depression of the accelerator. In view of this, the operation u kc to be performed on the mobile O k is a four-wheeled vehicle is determined by elements including acceleration and angular velocity. On the other hand, when the moving object Ok is a person, the operation u kc can be designated by the speed.

A more specific setting example of the operation u kc will be given. If mobile O k is an automobile, the acceleration -10~ + 30km / h / sec, taking a steering angle in a range of -7~ + 7deg / sec (specify the orientation in both code), the mobile O k is In the case of a person, the speed is 0 to 36 km / h, and the direction is 0 to 360 deg. In addition, all the quantities described here are continuous quantities. In such a case, an appropriate set of discretizations may be used to make the number of elements of each operation finite, and a set of operations {u kc } may be configured.

Thereafter, the moving body operation unit 52 operates the operation u kc selected in step S203 for a time Δt (step S204). The time Δt may be set to a value of about 0.1 to 0.5 (s), for example. Note that the value of Δt may be fixed, or may be a variable value depending on the urgency of the surrounding situation. In the following, an example in which Δt is a fixed value is shown. At this time, the trajectory generation time T is an integral multiple of Δt.

Subsequently, the determination unit 53, along with determining whether the internal state of the mobile O k after operating the operation u kc at step S204 satisfies a predetermined control condition (step S205), the operation u kc position of the movable body O k after operating the determines whether the movable region (step S206). Of these, determines the control condition in step S205 is defined according to the type of mobile O k, for example, when the mobile O k is a four-wheeled vehicle, and the speed range after the operation of step S204, It is determined by the vehicle G having the highest acceleration after the operation in step S204. On the other hand, the movable region determined in step S206 refers to a region such as a road (including a roadway and a sidewalk). Hereinafter, the case where the moving body is located in the movable region is expressed as “the moving condition is satisfied”.

As a result of the determination in the determination unit 53 described above, when there is a condition that does not satisfy even one (No in Step S205 or No in Step S206), the process returns to Step S202. In contrast, the determination in the determination unit 53 result in Yes, and step S206 in the case (step S205 that the position and the internal state of the mobile O k after the operation u kc terminated in step S204 satisfies all conditions In Yes), the time is advanced by Δt (t ← t + Δt), the position after the operation in step S204 is (x k (t), y k (t)), and the internal state is (v k (t), θ k (T)) (step S207).

The processes in steps S202 to S207 described above are repeated until the trajectory generation time T is reached. That is, when the time t newly defined in step S207 has not reached T (No in step S208), the process returns to step S203 and is repeated. On the other hand, if the newly defined time t in step S207 reaches T (Yes at step S208), and outputs the trajectory for the mobile O k, and stores it in the storage unit 14 (step S209).

Figure 4 is a time for the mobile O k t = 0, Δt, 2Δt, ···, the trajectory of the moving object O k generated by repeating a series of processes ranging from step S203 to step S207 in T It is a figure shown typically. The trajectory P k (m) (1 ≦ m ≦ N k , where m is a natural number) shown in the figure is a three-dimensional space-time (x, y, t) of two-dimensional space (x, y) and one-dimensional time (t). ). If this trajectory P k (m) is projected onto the xy plane, a predicted course of the moving object O k in the two-dimensional space (x, y) can be obtained.

After step S209, if the value of the counter n has not reached N k (No in step S210), the value of the counter n is incremented by 1 (step S211), the process returns to step S203, and the processes of steps S203 to S208 described above are performed. Repeat until the locus generation time T is reached.

If the counter n reaches N k at step S210 (Yes in step S210), generation of all trajectory for the mobile O k is completed. FIG. 5 shows a set of trajectories {P k composed of N k trajectories P k (1), P k (2),..., P k (N k ) generated for one moving object O k . It is explanatory drawing which shows typically ( nk )} on three-dimensional space time. The starting point, that is, the initial position (x k0 , y k0 , 0) of each trajectory forming the elements of the trajectory set {P k (n k )} is the same (see step S202). Note that FIG. 5 is a schematic diagram to the last, and the value of N k can take a value of, for example, about several thousand to several tens of thousands.

When the counter n reaches N k in step S210, and the counter k for moving object identification has not reached the total number K of moving objects (No in step S212), the value of the counter k is incremented by 1 and the number of times the trajectory is generated. The counter n is initialized to 1 (step S213), and the process returns to step S202 to repeat the process. On the other hand, when the counter k of the moving body reaches K (Yes in step S212), the trajectory generation for all the mobile bodies is completed, so the trajectory generation processing in step S2 is terminated, and the subsequent step S3 Proceed to

In this way, a plurality of movements existing within a predetermined range of the three-dimensional space-time are obtained by performing a predetermined number of times of trajectory generation processing on all the moving bodies detected by the sensor unit 3 and the vehicle exterior environment sensor 4. A spatiotemporal environment consisting of a set of trajectories that the body can take is formed. FIG. 6 is an explanatory diagram schematically illustrating a configuration example of a spatiotemporal environment. The spatiotemporal environment Env (P 1 , P 2 ) shown in the figure includes a trajectory set {P 1 (n 1 )} of the moving object O 1 (shown by a solid line in FIG. 6) and a trajectory set {P of the moving object O 2. 2 (n 2 )} (indicated by a broken line in FIG. 6). More specifically, in the spatiotemporal environment Env (P 1 , P 2 ), the two moving bodies O 1 and O 2 move in a + y-axis direction on a flat and straight road R like an expressway. It shows the spatiotemporal environment in the case of In this Embodiment 1, since the locus | trajectory generation | occurrence | production is independently performed for every moving body, without considering the correlation between moving bodies, the locus | trajectory of a different moving body may cross | intersect on space time.

6, the density per unit volume of the trajectory set in each region {P k (n k)} (k = 1,2) of the time-space, the density of presence probability of the moving object O k in each area of the spatio (Hereinafter referred to as “space-time probability density”). Therefore, by using the space environment Env (P 1, P 2) when configured by the trajectory generation processing at step S2, that determine the probability that the mobile O k passes through the predetermined region on when the three-dimensional space It becomes possible. Note that the spatiotemporal probability density described above is a probability concept in spatiotemporal, and therefore, it is not always 1 when the sum of the values of a single moving object is taken in spatiotemporal.

By the way, as for the specific value of the trajectory generation time T, when a fixed value is set in advance, if the trajectory is generated up to a value exceeding the value T, the probability density distribution in space-time becomes uniform. It is preferable to set a value that has no meaning even if it is calculated. For example, when the moving body is a four-wheeled vehicle and the four-wheeled vehicle is traveling normally, the maximum value may be about T = 5 (s). In this case, when the operation time Δt in step S204 is about 0.1 to 0.5 (s), a series of processing from step S203 to step S207 is performed to generate one trajectory P k (m). Repeat 10 to 50 times.

  Other roads such as expressways, ordinary roads, and two-lane roads that have different trajectory generation times T and that use position data to read the type of road that is currently running from map data, roads that apply image recognition, etc. It is preferable to perform switching by a method of reading the type of road with a recognition device.

  Also, using the trajectory calculated up to the trajectory generation time T, the probability density distribution in space-time is statistically evaluated. If the distribution is constant, the trajectory generation time T is reduced, and if not, It is preferable to perform adaptive control that increases the trajectory generation time T.

  Furthermore, it is also possible to prepare in advance a plurality of courses that can be taken by the host vehicle, and perform prediction until a trajectory generation time T at which the probability of the intersection between the course of the host vehicle and the course of each object is constant. Is possible. In this case, the termination condition may be that the increase in risk for each course that the vehicle can take when the predicted time is increased by Δt is constant. When taking this configuration, in order to obtain information to determine where to take the course now to ensure safety, the endpoints on the future side of the course that the vehicle can take are set to be widely distributed in space. Needless to say, it has been done.

After the trajectory generation processing for each moving object described above, the prediction unit 6 performs probabilistic prediction of the course that each moving object can take (step S3). Hereinafter, as a specific prediction calculation process in the prediction unit 6, the probability that a specific trajectory P k (m) is selected from the trajectory set {P k (n k )} generated for the moving object O k . However, it is a matter of course that this prediction calculation is only an example.

When N k trajectories of the moving body O k are generated, the probability p (P k (m)) that one of the trajectories P k (m) is an actual trajectory is calculated as follows. . First, the operation sequence {u km (t)} for realizing the trajectory P k (m) of the moving body O k is {u km (0), u km (Δt), u km (2Δt),. , U km (T)}, the probability that the operation u km (t) is selected at time t is p (u km (t)). The probability that km (t)} is executed is
Is required. Therefore, when the trajectory set of N k present in the mobile O k {P k (n k )} is given, the probability p (P k that one trajectory P k to the mobile O k can assume (m) is selected (M))
It becomes.

Here, when all operations u km (t) are selected with equal probability p 0 (where 0 <p 0 <1), Equation (1) becomes
It becomes. Therefore, the sum of the probabilities of the trajectories P k (m) included in the N k trajectories that can be taken by the mobile object O k is N k p 0 , where s is the number of discrete steps from t = 0 to t = T. s , and the probability p (P k (m)) that one trajectory P k (m) is selected is obtained by substituting Equation (3) into Equation (2).
It becomes. That is, the probability p (P k (m)) does not depend on the trajectory P k (m).

In Equation (4), if the number of trajectories generated for all moving objects is the same (N), N 1 = N 2 =... = N K = N (constant). p (P k (m)) = 1 / N, which is constant regardless of the moving object O k . In this case, the prediction calculation in the prediction unit 6 is simplified by normalizing the value of the probability p (P k (m)) to 1, and the predetermined prediction calculation can be executed more quickly.

In the prediction unit 6, per unit volume in each region of the three-dimensional space-time based on the probability p (P k (m)) calculated for each moving object O k (k = 1, 2,..., K). The existence probability of the moving object O k of the moving object O k is obtained, and the prediction result is obtained as trajectory information (possible course information) for each moving object O k (k = 1, 2,..., K) generated by the trajectory generation unit 5. At the same time, it is stored in the past own space-time environment storage unit 7. This existence probability corresponds to the spatio-temporal probability density on the three-dimensional space-time of the trajectory set {P k (n k )}, and the existence probability is generally large in the region where the density of the trajectory passing therethrough is high.

In subsequent step S4, the specific other vehicle course interference degree calculation unit 8 calculates the degree of interference between the specific other vehicle and a predetermined vehicle other than the specific other vehicle, in this case, the own vehicle (step S4). FIG. 7 is a flowchart showing an outline of the interference degree calculation process. In the following description, the moving body O 1 is a specific other vehicle (specific moving body). Further, for convenience of explanation, it is assumed that the other moving bodies O k (k = 2, 3,..., K) are all four-wheeled vehicles and are referred to as predetermined vehicles O k, and in particular, O 2 is the own vehicle. Here, the specific other vehicle O 1 corresponds to the vehicle specified by the specific other vehicle separating unit 10 from the moving body information acquired by the outside environment sensor 4. For example, the moving body that is present at the position closest to the host vehicle O 2 is selected as the specific other vehicle O 1 . The interference degree calculation process shown in FIG. 7 includes four loop processes. For all elements of the trajectory set {P 1 (n 1 )} of the specific other vehicle O 1 obtained in step S3, the predetermined vehicle The degree of interference between all trajectory sets {P k (n k )} of O k is calculated individually.

First, the iterative process (Loop 1) for all the trajectories of the specific other vehicle O 1 is started (step S401). At this time, one trajectory of the trajectory set {P 1 (n 1 )} is selected, and subsequent processing is executed on the selected trajectory.

Then, to start the iterative process (Loop2) for a given vehicle O k (step S402). In Loop 2, a vehicle identification counter k = 2 is initialized, and the value of k is increased each time the repetition process is completed.

In Loop 2, the iterative process (Loop 3) is performed for all elements of the trajectory set {P k (n k )} generated in Step S3 for the predetermined vehicle O k (Step S403). In this iterative process, the interference may be laid down by the counter k for repetition i.e. for identifying the counter n 1 and vehicle identification the generated trajectory for a particular other vehicle O 1 of Loop1 r 1 (n 1, k) And r 1 (n 1 , k) is set to 0 (step S404).

Subsequently, an iterative process (Loop 4) for evaluating the interference between the locus P 1 (n 1 ) of the specific other vehicle O 1 and the locus P k (n k ) of the predetermined vehicle O k is started (step S405). In Loop 4, the distances at the same time between the two trajectories P 1 (n 1 ) and the trajectory P k (n k ) are sequentially obtained at times t = 0, Δt,. Since the position of each trajectory in the two-dimensional space is defined as the center of each vehicle, the spatial distance between the two trajectories is smaller than a predetermined value (for example, the standard width or length of the vehicle). If, certain other vehicle O 1 and the predetermined vehicle O k can be regarded as a collision. In this sense, it may be determined that two moving bodies have collided even if the coordinate values of the two vehicles do not match. Hereinafter, the maximum distance that can be regarded as a collision of two vehicles (a spatial distance that interferes with each other) is referred to as an interference distance.

FIG. 8 is a diagram schematically showing a temporal and spatial relationship between the locus P 1 (n 1 ) of the specific other vehicle O 1 and the locus P k (n k ) of the predetermined vehicle O k . In the case shown in the figure, the locus P 1 (n 1 ) and the locus P k (n k ) intersect at two points C 1 and C 2 . Therefore, in the vicinity of the two points C 1 and C 2 , there are regions A 1 and A 2 in which the distance between the two loci at the same time is smaller than the interference distance. That is, it is determined that the specific other vehicle O 1 and the predetermined vehicle O k have collided at times when the two tracks P 1 (n 1 ) and the track P k (n k ) are included in the areas A 1 and A 2 , respectively. Is made. In other words, time t = 0, Δt, ···, among T, then the number of passes through the area A 1 and A 2 is the number collision between the vehicle O 1 and the other vehicle O k.

  As can be seen from FIG. 8, in the spatiotemporal environment formed in the first embodiment, even if two trajectories collide once, subsequent trajectories are generated. This is because the trajectory for each moving object is generated independently.

Result of obtaining distance specified other vehicle O 1 and the predetermined vehicle O k, if certain other vehicle O 1 and the predetermined vehicle O k in the sense described above is determined to have collided (Yes at step S406), the degree of interference The value of r 1 (n 1 , k) is
(Step S407). Here, the second item c 1k · p (P k (n k )) · F (t) will be described. The coefficient c 1k is a positive constant. For example, c 1k = 1 can be set. Further, p (P k (n k)) is a quantity defined by Equation (2) is the probability that one trajectory P k at a predetermined vehicle O k (n k) is selected. The last F (t) is an amount that gives time dependency of interference between moving bodies in one collision. Therefore, when the time dependency is not given to the interference between the moving bodies, the value of F (t) may be constant. On the other hand, when the time dependency is given to the interference between the moving bodies, for example, as shown in FIG. 9, F (t) as a function such that the value gradually decreases with time. May be defined. F (t) shown in FIG. 9 is applied when the most recent collision is regarded as important.

If the time t has not reached T after step S407, Loop4 is repeated (No in step S408). In this case, the value of t is increased by Δt (step S409), the process returns to step S405, and Loop 4 is repeated. On the other hand, if the time t has reached T after step S407, Loop4 is terminated (Yes in step S408). Incidentally, when a specific other vehicle O 1 and the predetermined vehicle O k at time t that do not collide, the process proceeds directly to the determination processing whether to repeat the Loop 4 (step S408).

Through the loop 4 iteration process described above, the value of the interference degree r 1 (n 1 , k) increases as the number of collisions increases. After this Loop4 is completed, in Step S410, it is determined whether or not Loop3 is repeated. That is, if any one is not performed interference evaluation with one trajectory P 1 specific other vehicle O 1 (n 1) of the generated trajectory for a given vehicle O k (No at step S410), n k is set to n k +1 (step S411), and the process returns to step S403 to repeat Loop3.

In contrast, if made interference evaluation all one trajectory P 1 specific of the resulting trajectory for a given vehicle O k other vehicle O 1 (n 1) (Yes in Step S410) imparts the final interference degree r 1 (n 1, k) evaluating interference between the trajectory P 1 specific other vehicle O 1 and (n 1) and the total trajectory of the predetermined vehicle O k (step S412) The given value is output and stored in the path-specific interference degree storage unit 9 (step S413).

Step S413 the final degree of interference r 1 output in (n 1, k) values of a total of the trajectory of a given vehicle O k, the probability one trajectory P k (n k) is selected p (P k (N k )). Therefore, in equation (5), the coefficient c 1k is constant (eg, c 1k = 1) regardless of k, F (t) is set to a constant (eg, 1), and the locus P 1 of the specific other vehicle O 1 is set. When (n 1) and the number of collisions between the trajectory P k (n k) of the other vehicle O k and M 1k (n 1, n k ), the value of the interference degree r 1 (n 1, k) is the trajectory P k (n k) for each of the probability p to (P k (n k)) took the sum the elements of M 1k (n 1, n k ) multiplied by all trajectories set the value {P k (n k)} Become a thing. This sum is none other than the collision probability of collision between one trajectory P 1 (n 1 ) of the specific other vehicle O 1 and a trajectory that the predetermined vehicle Ok can take. Therefore, value finally obtained as an interference degree r 1 (n 1, k) is increased in proportion to the collision probability of a trajectory P 1 specific other vehicle O 1 and (n 1) and the predetermined vehicle O k To do.

Subsequent to step S413, a determination process of whether or not to repeat Loop2 is performed. In the case (No in step S414) remaining predetermined vehicle O k should perform interference evaluation with specific other vehicle O 1, the value of k is increased by one (step S415), and repeats the Loop2 returns to step S402 . On the other hand, if there are no more predetermined vehicle O k should perform interference evaluation with specific other vehicle O 1 (Yes in step S414), the process proceeds to subsequent step S416.

In step S416, it is determined whether to repeat Loop1. Specifically, when the locus to be subjected to interference evaluation remains in the locus set {P 1 (n 1 )} of the specific other vehicle O 1 (No in step S416), the value of n 1 is set to 1. Increase (step S417), return to step S401, and repeat Loop1. On the other hand, if there is no remaining locus to be subjected to interference evaluation in the locus set {P 1 (n 1 )} of the specific other vehicle O 1 (Yes in step S416), Loop 1 is terminated and the interference degree calculation process is performed. (Step S4) ends.

Incidentally, the specific other vehicle course interference level calculation unit 8, it is assumed for calculating the degree of interference r 1 (n 1, k) for all the predetermined vehicle O k of specific other vehicle O 1, at least a specific other vehicle O 1 What is necessary is just to calculate the interference degree r 1 (n 1 , 2) with respect to the own vehicle O 2 .

On the other hand, in parallel with the processing of steps S2 to S4, certain other vehicle separation unit 10, actual moving path storing operation time actual moving position of the interval in the environment outside the vehicle sensor 4 sequentially specified other vehicle O 1 obtained from the Δt By accumulating the data in the unit 11, the travel path actually taken by the specific other vehicle O 1 during the trajectory generation time T is reproduced in the three-dimensional space-time by going back in time and space by the trajectory generation time T. (Step S5).

Then, the similar other vehicle route search unit 13 generates and predicts a path that is most similar to the actual travel route recognized by the specific other vehicle O 1 as a route that can be taken by the specific other vehicle O 1. Search from the set of trajectories {P 1 (n 1 )} stored in the self-other time-space environment storage unit 7 and calculate the specific other-vehicle path interference degree for the searched similar trajectory (path) P 1 (m). The degree of interference r 1 (n 1 , 2) for the host vehicle O 2 calculated by the unit 8 and stored in the path-specific interference degree storage unit 9 is extracted and output to the output terminal 12 (step S6). Here, the search for similar trajectories may be performed by calculating the square error of the movement position at each time t = 0, Δt, 2Δt,..., T, and selecting the trajectory with the smallest sum of square errors.

FIG. 10 is a diagram schematically illustrating, for example, a state in which the actual travel route P 1 (R) of the specific other vehicle O 1 is reproduced on the three-dimensional space-time retroactively by the trajectory generation time T. That is, the actual travel path P 1 (R) is formed by accumulating the actual travel position of the specific other vehicle O 1 for each operation time t = 0, Δt, 2Δt,. Then, since the trajectory (track) P 1 (m) of the trajectory set {P 1 (n 1 )} is most similar to the actual travel path P 1 (R), the trajectory P 1 (m) Is searched for as the most similar route, and the degree of interference r 1 (n 1 , 2) with respect to the vehicle O 2 calculated in advance for the locus P 1 (m) is extracted from the route-specific interference degree storage unit 9 and specified, etc. It is output as a safety evaluation value for the vehicle O 1 with respect to the own vehicle O 2 .

In other words, the travel path of the designated specific other vehicle O 1 actually taken in the past 5 seconds is composed of the paths that can be taken by the specific other vehicle O 1 and the own vehicle O 2 predicted 5 seconds ago. The degree of safety (or danger) in other space-time environments is evaluated by the collision probability.

  According to the first embodiment of the present invention described above, the positions and internal states of the plurality of moving bodies are read from the storage means, and each of the plurality of moving bodies is set to the time based on the read positions and internal states of the moving bodies. The position change that can be taken with the passage of time is generated as a trajectory in time and space composed of time and space, and the generated trajectory is used to make a probabilistic prediction of the course of a plurality of moving objects in the storage means Based on the result stored and stored in the storage means, the degree of interference that quantitatively indicates the degree of interference with the path that the predetermined moving body can take for each path that the specific moving body can take. Calculate and store in the storage means, cumulatively store the actual moving position of the specific moving body at a predetermined time interval, and recognize the actual moving path of the specific moving body in time and space Specific mobile objects In the obtained route, the route that is most similar to the recognized actual moving route is searched for, and the degree of interference calculated for the searched similar route and stored in the storage means is evaluated for the safety of the specific moving body. Since it is extracted as a value, in the environment of a moving path that is expected to be taken by both a specific moving body and a predetermined moving body, the moving path of what risk level the specific moving body actually has It is possible to recognize the degree of danger that the specific moving object has allowed by moving back and forth in time and space, and thus the behavior of such a specific moving object can be recognized. By recognizing the vehicle, it is possible to ensure safety even in situations that may occur in reality when the vehicle (predetermined moving body) is automated.

  Further, according to the first embodiment, it is possible to accurately determine the possibility of a collision with another moving body by applying an interference degree defined using a collision probability in space-time. it can.

Note that the coefficient c 1k in equation (5) when increasing the value of the interference degree r 1 (n 1 , k) is not necessarily a constant. For example, the coefficient c 1k may be a magnitude of relative velocity of the collision point with a specific other vehicle O 1 and the predetermined vehicle O k. In general, the greater the relative speed, the greater the impact during a collision. Therefore, when the coefficient c 1k is the magnitude of the relative speed at the time of the collision between the vehicles, the impact degree of the collision between the vehicles is added to the interference degree r 1 (n 1 , k).

  By the way, the first embodiment can also be applied to a four-dimensional space-time (space three-dimensional, time one-dimensional) as described above. In this case, not only can it be applied to a vehicle traveling on a road with a height difference, but other moving objects that move in the air are also moving in the air, such as airplanes and helicopters. The present invention can also be applied when performing the course prediction.

  Here, the difference between the non-patent document 1 cited in the background art and the first embodiment will be described. Both of these two technologies perform the course prediction of the moving body using the probability concept, but in Non-Patent Document 1, the course of the moving body within a predetermined range is not independently predicted. Probability calculation based on mutual correlation is performed. For this reason, when any two of the plurality of moving bodies collide, the course prediction of the two moving bodies ends when the collision occurs. This means that, when considered on a three-dimensional space-time, the trajectories of two different moving objects are not searched after the point of intersection.

  On the other hand, in the first embodiment, since the trajectories of the moving objects are generated independently for each moving object, even if trajectories of different moving objects intersect in the three-dimensional space-time, those trajectories are predetermined. Generated until time passes. As described above, the spatiotemporal environment generated in Non-Patent Document 1 and the spatiotemporal environment generated in the first embodiment are completely different.

Further, in the first embodiment, since the independent route search is performed for each moving body without considering the correlation of the moving bodies, the calculation amount is less than that of Non-Patent Document 1. In particular, in the first embodiment, the number of times of calculating the interference degree for each trajectory is
Therefore, a calculation amount of the order of the square of the number of trajectories is sufficient regardless of the total number of moving objects constituting the spatiotemporal environment. On the other hand, when performing interference evaluation in Non-Patent Document 1, a specific moving body (own vehicle) and other moving bodies (other vehicles) are not distinguished from each other. The amount of calculation (corresponding to the number of times of calculating the interference degree in the first embodiment) is
Therefore, a calculation amount on the order of the Kth power of the number of trajectories is required. As a result, the greater the number of moving bodies that make up the spatiotemporal environment, the more significantly the difference from the calculation amount of the first embodiment.

  In addition, in Non-Patent Document 1, even when a phenomenon of a collision can be predicted, it is not possible to grasp when it occurs. This is because Non-Patent Document 1 does not seek the probability that a moving object will collide in the flow of time but focuses on searching for the presence or absence of a collision for each state at each time. In other words, Non-Patent Document 1 does not explicitly use a spatiotemporal environment and does not reach the concept of spatiotemporal probability density.

  As described above, both of the first embodiment and Non-Patent Document 1 perform course prediction using the probability concept, and at first glance, it may give an impression as if it is a similar technique. The essence of the technical idea is completely different, and it is extremely difficult for those skilled in the art to arrive at the first embodiment from Non-Patent Document 1.

(Embodiment 2)
In the second embodiment of the present invention, the position and internal state of the vehicle O 2 that is the designated predetermined moving body is read from the storage means, and the vehicle is based on the read position and internal state of the vehicle O 2. A change in the position that O 2 can take as time elapses is generated as a trajectory on a time space composed of time and space, and a probabilistic prediction of the course of the vehicle O 2 is made by using the generated trajectory. may be stored in the carried storage means, the actual movement path of the particular other vehicle O 1 and cumulatively stores the actual moving position of the specific other vehicle O 1 is a particular mobile at a predetermined time interval While recognizing retroactively in time and space, based on the result predicted by the prediction process and stored in the storage means, the recognized actual moving route of the specific other vehicle O 1 with respect to the route that the own vehicle O 2 can take. Identifies the degree of interference that quantitatively indicates the degree of interference It is obtained to calculate the safety evaluation value of the vehicle O 1.

Therefore, the mobile safety evaluation apparatus 20 of the second embodiment, instead of the trajectory generation unit 5 vehicle O 2 only the trajectory in space when (may be only the predetermined vehicle O k) A trajectory generating unit 21 for generating, a predicting unit 22 for performing probabilistic prediction of the course of only the own vehicle O 2 instead of the predicting unit 6, and the own vehicle O instead of the past own time / space-time environment storage unit 7. with two only of the predicted past vehicle spatiotemporal environment storage unit 23 that stores the spatial environment when was the actual moving path is specified other vehicle O 1 taken in place of a specific other vehicle course interference level calculation unit 8 P 1 A specific other vehicle interference degree calculation unit 24 that calculates and outputs an interference degree with respect to the trajectory set {P 2 (n 2 )} of the own vehicle O 2 of (R) is provided.

FIG. 12 is a diagram schematically illustrating an example of a spatio-temporal environment with the own vehicle when the actual moving route P 1 (R) is used without using the predicted route for the specific other vehicle O 1 . 6 corresponds to FIG. That is, the trajectory set {P 2 (n 2 )} of the own vehicle O 2 in the three-dimensional space-time environment is the same as that in FIG. 6, but the specific other vehicle O 1 is actually in the three-dimensional space-time environment. The travel route P 1 (R) is reproduced as only one track (track), and the specific other vehicle route interference degree calculation unit 24 calculates the degree of interference with the track set {P 2 (n 2 )} of the own vehicle O 2. To be served.

In this way, with respect to the specific other vehicle O 1 , if the actual moving route P 1 (R) is directly applied without using the predicted route, the situation can be simplified and the behavior can be improved in the case where there are many surrounding moving bodies. It is possible to evaluate, and it is possible to reduce the amount of calculation in the trajectory generation unit 21 and the prediction unit 22 and the specific other vehicle course interference degree calculation unit 24.

  In these Embodiments 1 and 2, the mobile body safety evaluation devices 1 and 20 are mounted on the own vehicle, and the specific other vehicle actually takes a moving path with respect to the own vehicle. However, the present invention is not limited to such an application example. For example, a mobile body safety evaluation device is installed on the side of an administrator who manages an expressway, and with respect to any other vehicles traveling on the expressway, one specified other vehicle and the other as a specified vehicle are specified other vehicles. On the other hand, it may be possible to evaluate and monitor what risk value movement course is actually taken. In this case, what is necessary is just to replace the handling regarding the own vehicle demonstrated in FIG. 1 etc. with a predetermined vehicle.

It is a block diagram which shows the function structure of the mobile body safety evaluation apparatus which concerns on Embodiment 1 of this invention. It is a flowchart which shows the outline | summary of the mobile body safety evaluation method which concerns on Embodiment 1 of this invention. It is a flowchart which shows the outline | summary of the locus | trajectory generation process in the mobile body safety evaluation method which concerns on Embodiment 1 of this invention. It is a figure which shows typically the locus | trajectory produced | generated in three-dimensional space time. It is a figure which shows typically the locus | trajectory set produced | generated in three-dimensional space-time with respect to one moving body. It is explanatory drawing which shows the structure of a spatiotemporal environment typically. It is a flowchart which shows the outline | summary of the interference degree calculation process in the mobile body safety evaluation method which concerns on Embodiment 1 of this invention. It is a figure which shows typically the relationship in time space of one locus | trajectory of a specific other vehicle, and one locus | trajectory of the own vehicle. It is a figure which shows the example of the function which gives the time dependence of the interference between moving bodies. It is a figure which shows typically a mode that the actual movement course of the specific other vehicle was reproduced on the three-dimensional space-time retroactively by the locus | trajectory generation time. It is a block diagram which shows the function structure of the mobile body safety evaluation apparatus which concerns on Embodiment 2 of this invention. It is a figure which shows typically a mode that the actual movement course of the specific other vehicle was reproduced on the three-dimensional space-time retroactively by the locus | trajectory generation time.

Explanation of symbols

DESCRIPTION OF SYMBOLS 5 Trajectory production | generation part 6 Prediction part 7 Past self-other space-time environment memory | storage part 8 Specific other vehicle course interference degree calculation part 9 Interference course memory part 10 Specific other vehicle separation part 11 Actual movement course storage part 13 Similar other vehicle course search Unit 21 Trajectory generation unit 22 Prediction unit 23 Past vehicle space-time environment storage unit 24 Specific other vehicle course interference calculation unit

Claims (14)

  1. Other than the specific moving body of the moving path of the specific moving body included in the plurality of moving bodies by using storage means for storing at least the position of the plurality of moving bodies and the internal state including the speed of each moving body A mobile body safety evaluation method for evaluating safety for a predetermined mobile body,
    The position and the internal state of the plurality of moving bodies are read from the storage means, and based on the read position and the internal state of the moving body, the change of the position that each of the plurality of moving bodies can take with time is changed. And a trajectory generation step for generating each as a trajectory on a spatiotemporal space composed of space,
    A prediction step of performing probabilistic prediction of the course of the plurality of moving objects by using the trajectory generated in the trajectory generation step and storing the path in the storage unit;
    Interference that quantitatively indicates the degree of interference with the path that can be taken by the predetermined moving body for each course that can be taken by the specific moving body based on the result predicted in the prediction step and stored in the storage means An interference degree calculating step of calculating a degree and storing the degree in the storage means;
    An actual moving path recognition step of accumulating the actual moving position of the specific moving body at a predetermined time interval and recognizing the actual moving path of the specific moving body in time and space;
    Among the paths that can be taken by the specific moving body, the path that is most similar to the recognized actual moving path is searched for, and the interference degree calculated for the searched similar path and stored in the storage means A similar path search step for extracting a safety evaluation value of the specific moving object,
    A mobile body safety evaluation method characterized by comprising:
  2. Other than the specific moving body of the moving path of the specific moving body included in the plurality of moving bodies by using storage means for storing at least the position of the plurality of moving bodies and the internal state including the speed of each moving body A mobile body safety evaluation method for evaluating safety for a predetermined mobile body,
    The position and the internal state of the predetermined moving body are read from the storage unit, and the change in the position that the predetermined moving body can take over time is determined based on the read position and internal state of the predetermined moving body. And a trajectory generation step for generating a trajectory in space-time composed of space,
    A prediction step of performing a probabilistic prediction of the path of the predetermined moving body by using the locus generated in the locus generation step and storing it in the storage means;
    An actual moving path recognition step of accumulating the actual moving position of the specific moving body at a predetermined time interval and recognizing the actual moving path of the specific moving body in time and space;
    Based on the result predicted in the prediction step and stored in the storage unit, the degree of interference of the recognized moving path of the specific moving body with respect to the path that the predetermined moving body can take is quantitatively determined. An interference degree calculating step of calculating an interference degree to be indicated as a safety evaluation value of the specific moving body;
    A mobile body safety evaluation method characterized by comprising:
  3. The trajectory generation step includes
    An operation selection step of selecting an operation for the object from a plurality of operations;
    An object operation step for operating the operation selected in the operation selection step for a predetermined time;
    Determining whether or not the position and internal state of the object after operating the selected operation in the object operation step satisfy a control condition related to the control of the object and a movement condition related to the movable region of the object Steps,
    Including
    The mobile body safety evaluation method according to claim 1, wherein a series of processing from the operation selection step to the determination step is repeatedly performed until a trajectory generation time for generating a trajectory is reached.
  4. The operation selection step selects an operation according to an operation selection probability given to each of the plurality of operations,
    4. As a result of the determination in the determination step, when the position and internal state of the object satisfy the control condition and the movement condition, the time is advanced to return to the operation selection step. Mobile body safety evaluation method.
  5.   The mobile operation safety evaluation method according to claim 4, wherein the operation selection probability is defined using a random number.
  6.   The mobile body safety evaluation method according to claim 4 or 5, wherein the number of trajectories to be generated in the trajectory generation step is predetermined.
  7. The predetermined moving body is a host vehicle,
    The said specific mobile body is the specific other vehicle which exists in the circumference | surroundings of the said own vehicle and becomes object, The mobile body safety evaluation method as described in any one of Claims 1-6 characterized by the above-mentioned.
  8. A mobile body safety evaluation device that evaluates safety of a specific mobile body other than the specific mobile body in a moving path of the specific mobile body included in the plurality of mobile bodies,
    Storage means for storing at least the positions of a plurality of moving bodies and an internal state including the speed of each moving body;
    The position and the internal state of the plurality of moving bodies are read from the storage means, and based on the read position and internal state of the moving body, the change in the position that each of the plurality of moving bodies can take with the passage of time is determined over time. And trajectory generating means for generating each as a trajectory on a time space composed of space,
    Predicting means for performing probabilistic prediction of the course of the plurality of moving bodies by using the trajectory generated by the trajectory generating means, and storing in the storage means;
    Interference that quantitatively indicates the degree of interference with the path that can be taken by the predetermined moving body for each course that can be taken by the specific moving body based on the result predicted by the predicting means and stored in the storage means An interference degree calculating means for calculating a degree and storing it in the storage means;
    An actual movement path recognition means for accumulating the actual movement position of the specific moving body at a predetermined time interval and recognizing the actual movement path of the specific moving body in space-time;
    Among the paths that can be taken by the specific moving body, the path that is most similar to the recognized actual moving path is searched for, and the interference degree calculated for the searched similar path and stored in the storage means Similar path search means for extracting the value as a safety evaluation value of the specific moving body,
    A mobile body safety evaluation apparatus comprising:
  9. A mobile body safety evaluation device that evaluates safety of a specific mobile body other than the specific mobile body in a moving path of the specific mobile body included in the plurality of mobile bodies,
    Storage means for storing at least the positions of a plurality of moving bodies and an internal state including the speed of each moving body;
    The position and the internal state of the predetermined moving body are read from the storage unit, and the change in the position that the predetermined moving body can take over time is determined based on the read position and internal state of the predetermined moving body. And a trajectory generating means for generating a trajectory on a spatiotemporal space composed of space,
    Predicting means for performing probabilistic prediction of the course of the predetermined moving body by using the trajectory generated by the trajectory generating means, and storing it in the storage means;
    An actual movement path recognition means for accumulating the actual movement position of the specific moving body at a predetermined time interval and recognizing the actual movement path of the specific moving body in space-time;
    Based on the result predicted by the prediction unit and stored in the storage unit, the degree of interference of the recognized moving path of the specific moving body with respect to the path that the predetermined moving body can take is quantitatively determined. An interference degree calculating means for calculating an interference degree to be indicated as a safety evaluation value of the specific moving body;
    A mobile body safety evaluation apparatus comprising:
  10. The trajectory generating means includes
    An operation selecting means for selecting an operation for the object from a plurality of operations;
    Object operating means for operating the operation selected by the operation selecting means for a predetermined time;
    Determining whether or not the position and internal state of the object after the selected operation is operated by the object operation means satisfy a control condition related to the control of the object and a movement condition related to the movable area of the object Means,
    Including
    The mobile body safety according to claim 8 or 9, wherein a series of processing from operation selection processing by the operation selection means to determination processing by the determination means is repeated until a trajectory generation time for generating a trajectory is reached. Sex evaluation device.
  11. The operation selection means selects an operation according to an operation selection probability given to each of the plurality of operations,
    As a result of the determination by the determination means, when the position and internal state of the object satisfy the control condition and the movement condition, the operation selection process by the operation selection means is returned by advancing time. The mobile body safety evaluation apparatus according to claim 10.
  12.   The mobile unit safety evaluation apparatus according to claim 11, wherein the operation selection probability is defined using a random number.
  13.   The mobile body safety evaluation apparatus according to claim 11 or 12, wherein the number of trajectories to be generated by the trajectory generation means is predetermined.
  14. The predetermined moving body is a host vehicle on which the evaluation device is mounted,
    The mobile body safety evaluation apparatus according to any one of claims 8 to 13, wherein the specific mobile body is a specific other vehicle that is present around the host vehicle.
JP2006055442A 2006-03-01 2006-03-01 Mobile body safety evaluation method and mobile body safety evaluation apparatus Active JP4730137B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2006055442A JP4730137B2 (en) 2006-03-01 2006-03-01 Mobile body safety evaluation method and mobile body safety evaluation apparatus

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2006055442A JP4730137B2 (en) 2006-03-01 2006-03-01 Mobile body safety evaluation method and mobile body safety evaluation apparatus

Publications (2)

Publication Number Publication Date
JP2007233765A JP2007233765A (en) 2007-09-13
JP4730137B2 true JP4730137B2 (en) 2011-07-20

Family

ID=38554293

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2006055442A Active JP4730137B2 (en) 2006-03-01 2006-03-01 Mobile body safety evaluation method and mobile body safety evaluation apparatus

Country Status (1)

Country Link
JP (1) JP4730137B2 (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5098584B2 (en) * 2007-11-09 2012-12-12 日産自動車株式会社 Vehicle driving support device
DE102008062916A1 (en) * 2008-12-23 2010-06-24 Continental Safety Engineering International Gmbh Method for determining a collision probability of a vehicle with a living being
JP4957747B2 (en) 2009-05-18 2012-06-20 トヨタ自動車株式会社 Vehicle environment estimation device
EP2950294B1 (en) * 2014-05-30 2019-05-08 Honda Research Institute Europe GmbH Method and vehicle with an advanced driver assistance system for risk-based traffic scene analysis

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2799375B2 (en) * 1993-09-30 1998-09-17 本田技研工業株式会社 Anti-collision device
JP2004514185A (en) * 1999-09-13 2004-05-13 エアビクティ インコーポレイテッド Closed loop tracking system
JP3501009B2 (en) * 1999-03-26 2004-02-23 トヨタ自動車株式会社 Vehicle collision avoidance control device
JP2001125646A (en) * 1999-10-26 2001-05-11 Honda Motor Co Ltd Movable printer and printed matter delivering method
JP3896852B2 (en) * 2002-01-16 2007-03-22 株式会社デンソー Vehicle collision damage reduction device
JP3714258B2 (en) * 2002-02-01 2005-11-09 日産自動車株式会社 Recommended operation amount generator for vehicles
JP2004145479A (en) * 2002-10-22 2004-05-20 Aisin Seiki Co Ltd Device for providing peripheral vehicle information
JP2005227978A (en) * 2004-02-12 2005-08-25 Denso Corp Collision avoidance system

Also Published As

Publication number Publication date
JP2007233765A (en) 2007-09-13

Similar Documents

Publication Publication Date Title
CN108698595B (en) For controlling the method for vehicle movement and the control system of vehicle
JP6544908B2 (en) Complex reliability estimation for predictive driver assistance systems
JP2019533609A (en) Near-crash determination system and method
CN106952471B (en) Prediction of driver intent at an intersection
US9463797B2 (en) Method and vehicle with an advanced driver assistance system for risk-based traffic scene analysis
JP5580852B2 (en) Method, system, program, and vehicle for predicting movement of traffic participant
DE102013214328B4 (en) Vehicle behavior prediction device and vehicle behavior prediction method
Laugier et al. Probabilistic analysis of dynamic scenes and collision risks assessment to improve driving safety
EP2615598B1 (en) Vehicle with computing means for monitoring and predicting traffic participant objects
Lefèvre et al. Risk assessment at road intersections: Comparing intention and expectation
US9889858B2 (en) Confidence estimation for predictive driver assistance systems based on plausibility rules
Darms et al. Obstacle detection and tracking for the urban challenge
US9132775B2 (en) Mobile object target state determination device and program
Lawitzky et al. Interactive scene prediction for automotive applications
JP5475138B2 (en) Moving object prediction apparatus, virtual movable object prediction apparatus, program, moving object prediction method, and virtual movable object prediction method
Baskar et al. Traffic control and intelligent vehicle highway systems: a survey
US20140340242A1 (en) Method for Providing Parking Information on Free Parking Spaces
US8788134B1 (en) Autonomous driving merge management system
CN101395649B (en) Obstacle detection method, obstacle detection device
JP4623057B2 (en) Moving area acquisition device for own vehicle
EP2084690B1 (en) Cruise control plan evaluation device and method
EP2495713B1 (en) Driving support device
US10102750B2 (en) Object path prediction method, apparatus, and program, and automatic operation system
JP5206752B2 (en) Driving environment recognition device
CN104554258B (en) Using the path planning of the avoidance steering operation of virtual potential field technology

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20090204

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20101202

A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20110322

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20110404

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20140428

Year of fee payment: 3

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20140428

Year of fee payment: 3