US20140195093A1 - Autonomous Driving Merge Management System - Google Patents

Autonomous Driving Merge Management System Download PDF

Info

Publication number
US20140195093A1
US20140195093A1 US13/733,919 US201313733919A US2014195093A1 US 20140195093 A1 US20140195093 A1 US 20140195093A1 US 201313733919 A US201313733919 A US 201313733919A US 2014195093 A1 US2014195093 A1 US 2014195093A1
Authority
US
United States
Prior art keywords
vehicle
merging
cost
intention
merge
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.)
Granted
Application number
US13/733,919
Other versions
US8788134B1 (en
Inventor
Bakhtiar Brian Litkouhi
Junqing Wei
John M. Dolan
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Carnegie Mellon University
GM Global Technology Operations LLC
Original Assignee
Carnegie Mellon University
GM Global Technology Operations LLC
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 Carnegie Mellon University, GM Global Technology Operations LLC filed Critical Carnegie Mellon University
Priority to US13/733,919 priority Critical patent/US8788134B1/en
Assigned to GM Global Technology Operations LLC, CARNEGIE MELLON UNIVERSITY reassignment GM Global Technology Operations LLC ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: DOLAN, JOHN M., LITKOUHI, BAKHTIAR BRIAN, WEI, JUNQING
Assigned to WILMINGTON TRUST COMPANY reassignment WILMINGTON TRUST COMPANY SECURITY INTEREST Assignors: GM Global Technology Operations LLC
Publication of US20140195093A1 publication Critical patent/US20140195093A1/en
Publication of US8788134B1 publication Critical patent/US8788134B1/en
Application granted granted Critical
Assigned to GM Global Technology Operations LLC reassignment GM Global Technology Operations LLC RELEASE BY SECURED PARTY (SEE DOCUMENT FOR DETAILS). Assignors: WILMINGTON TRUST COMPANY
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B62LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
    • B62DMOTOR VEHICLES; TRAILERS
    • B62D15/00Steering not otherwise provided for
    • B62D15/02Steering position indicators ; Steering position determination; Steering aids
    • B62D15/025Active steering aids, e.g. helping the driver by actively influencing the steering system after environment evaluation
    • B62D15/0255Automatic changing of lane, e.g. for passing another vehicle
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
    • B60W30/14Adaptive cruise control
    • B60W30/16Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
    • B60W30/18Propelling the vehicle
    • B60W30/18009Propelling the vehicle related to particular drive situations
    • B60W30/18163Lane change; Overtaking manoeuvres
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/16Anti-collision systems
    • G08G1/167Driving aids for lane monitoring, lane changing, e.g. blind spot detection

Abstract

An autonomous driving merge management system includes an autonomous driving control device and an intention decision management system. The management system includes a candidate strategy subsystem generating a plurality of candidate driving strategies, a merging vehicle behavior recognition subsystem predicting a merging intention of a merging vehicle; an intention-based interactive prediction subsystem predicting future merging scenarios between the host vehicle and merging vehicle as a function of inputs by the merging vehicle behavior recognition subsystem and inputs by the candidate strategy subsystem, and a cost function-based evaluation subsystem determining a cost for each future merging scenario generated by the intention-based interactive prediction subsystem. A processor selects a merge strategy of the host vehicle based on intention-based prediction results and cost function-based evaluation results. The autonomous driving control device applies the merge strategy to the host vehicle for allowing the merging vehicle to cooperatively merge with the host vehicle.

Description

    BACKGROUND OF INVENTION
  • An embodiment relates generally to autonomous traffic merging behaviors.
  • Merging maneuvers includes at least one vehicle traveling in separate lanes wherein the vehicle must merge into a single lane of travel. The merging maneuver is performed implicitly by the driver of each vehicle wherein the driver individually decides whether they should merge in front of or behind the other vehicle. That is, each driver is not in communication with the other drivers and must make a decision on what merging position should be executed based on their observance of the relative position and speed between the two vehicles. The merging vehicle may speed up to merge ahead of the vehicle on the thoroughfare or slow down to merge behind the vehicle on the thoroughfare. Alternatively, the vehicle on the thoroughfare may speed up or slow down to accommodate the merging vehicle. In addition, the vehicle traveling on the thoroughfare may change lanes to accommodate the merging vehicle.
  • Often times drivers may choose to perform the same action as the other vehicle resulting in both vehicles accelerating or both vehicle decelerating at the same time thereby causing one of the vehicles to brake after it is realized that both vehicles are attempting a same acceleration action or deceleration action. As a result, one of the vehicles may brake to avoid a collision when it is apparent to one of the drivers that both drivers have the same intention such as merging ahead of the other vehicle. A change of speed such as braking may cause a chain of braking events for vehicles trailing the braking vehicle, which may ultimately lead to a traffic slow down or collision.
  • SUMMARY OF INVENTION
  • An advantage of an embodiment is an autonomous and cooperative merging between a merging vehicle and a host vehicle by recognizing the merging vehicles merging intentions and uses a cost technique to perform cooperative social behavior for merging the merging vehicle into traffic. An intention estimator extracts a probability of surrounding vehicles intentions in real time. Then for each surrounding candidate vehicle, a strategy is determined and a prediction engine considers the interaction between a host vehicle and surrounding candidate vehicle to predict future scenarios. Cost function-based evaluations are applied to determine the cost for each scenario and select the decision corresponding to the lowest cost.
  • An embodiment contemplates a method for autonomously controlling a vehicle speed during a merging maneuver between a host vehicle and a merging vehicle. Speed data and position data of the host vehicle and the remote data are obtained. A plurality of candidate driving strategies is generated by a processor. Each candidate driving strategy is a potential driving strategy executable by the host vehicle. An intention of the merging vehicle to merge forward or rearward of the host vehicle is predicted by the processor. A plurality of merging scenarios between the host vehicle and merging vehicle is generated by the processor as a function of a predicted merging intention of the merging vehicle and the plurality of candidate driving strategies. A cost for each merging scenario is determined by the processor based on a cost function evaluation analysis technique. A merge strategy of the host vehicle is selected by the processor based on the cost function evaluation results. Accelerations of a host vehicle are autonomously controlled using an autonomous driving control device. The autonomous driving control device applies the merge strategy to the host vehicle for cooperatively allowing the merging vehicle to cooperatively merge with the host vehicle.
  • An embodiment contemplates an autonomous driving merge management system that comprises an autonomous driving control device for autonomously controlling accelerations of a host vehicle and an intention decision management system. The intention decision management system comprises a candidate strategy subsystem generating a plurality of candidate driving strategies where each candidate driving strategy is a potential driving strategy executable by the host vehicle. A merging vehicle behavior recognition subsystem predicts a merging intention of a merging vehicle. The merging intention relates to a positive acceleration or a negative acceleration of the merging vehicle. An intention-based interactive prediction subsystem predicts future merging scenarios between the host vehicle and merging vehicle as a function of inputs by the merging vehicle behavior recognition subsystem and inputs by the candidate strategy subsystem. A cost function-based evaluation subsystem determines a cost for each future merging scenario generated by the intention-based interactive prediction subsystem. A processor selects a merge strategy of the host vehicle based on intention-based prediction results and cost function-based evaluation results. The autonomous driving control device applies the merge strategy to the host vehicle for allowing the merging vehicle to cooperatively merge with the host vehicle.
  • BRIEF DESCRIPTION OF DRAWINGS
  • FIG. 1 is a block diagram of an intention-integrated prediction- and cost function-based system.
  • FIG. 2 is an illustration of a freeway entrance ramp with merging vehicles.
  • FIG. 3 is an illustration of a freeway entrance ramp identifying key positions along the entrance ramp.
  • FIG. 4 a represents a simulation result for a merging vehicle given an intention to yield.
  • FIG. 4 b represents a simulation result for a merging vehicle given an intention not to yield.
  • FIG. 5 illustrates a graph identifying exemplary probability estimates of merging vehicle accelerations given two possible merging intentions.
  • FIG. 6 a illustrates is an exemplary estimated probability of a merging intention to yield.
  • FIG. 6 b illustrates a corresponding entrance ramp scenario at a first and second time period.
  • FIG. 7 is a plot of discretization velocity strategies.
  • FIG. 8 a illustrates a speed plot of the host and merging vehicle using adaptive cruise control.
  • FIG. 8 b illustrates a lateral and longitudinal plot of the host and merging vehicle using adaptive cruise control.
  • FIG. 9 a illustrates a speed plot of the host and merging vehicle using geographical-based adaptive cruise control.
  • FIG. 9 b illustrates a lateral and longitudinal plot of the host and merging vehicle using geographical-based adaptive cruise control.
  • FIG. 10 a illustrates a speed plot of the host and merging vehicle using the iPCB system.
  • FIG. 10 b illustrates a lateral and longitudinal plot of the host and merging vehicle using the iPCB system.
  • DETAILED DESCRIPTION
  • The availability of freeway and highway transportation has strongly contributed to efficient and faster travel between two locations. However, traffic congestion on road networks, including highways and freeways has become a bottleneck for further development of cities when the populated use of the roads grows well beyond the initial intended capacity. Autonomous vehicles have shown a potential to lessen this problem by reducing the number of traffic accidents and greatly increasing the capacity and efficiency of the transportation system. Recently, autonomous vehicle intelligence has increased from lane centering to actually driving on public roads with lane-changing capability. Nevertheless, human-driven vehicles still continue to be the dominate controls for driving a vehicle.
  • For human drivers, an intuitive cooperation occurs when a merging vehicle is nearby, consisting in an estimate of the other driver's intention and a corresponding reaction. Without intuition, in scenarios such as entrance ramps onto highways and freeways, it is difficult for an autonomous robot to behave in what might be termed a socially acceptable manner. Consequently, this will make it difficult for human drivers to understand, predict, and cooperate with autonomous vehicles.
  • There are few platforms that attempt to cooperatively interact between a human driver and an autonomous vehicle. System platforms include lane centering and cruise control-level autonomous driving on highways. Such autonomous vehicles are able to deal with relatively light human traffic; however, these vehicles do not perform as well in heavy traffic in comparison to human drivers due to their limited ability to understand and cooperate with surrounding cars.
  • Adaptive Cruise Control (ACC) is one of the most widely deployed advanced driver assist systems. This system senses a vehicle forward of the vehicle and attempts to maintain a minimum spacing between the autonomous driven vehicle and the vehicle forward of the autonomous vehicle. However, the problem with ACC systems is that the system is only capable of limited single-lane highway autonomy.
  • In human driver behavior models, experienced human drivers can understand each other's intentions and smoothly cooperate with each other while driving. Therefore, it is reasonable to utilize a human driver behavior model to control an autonomous vehicle. However, it has been found that in such models, temporal and some unobservable state information (e.g. intention) of surrounding vehicles are not used because of the difficulty of data collection and complexity of model training. Therefore, such systems have difficulty emulating human decisions at the social cooperation level.
  • In a fully autonomous driving system, a motion planner typically commands the vehicle's lateral and longitudinal movements. The most straightforward way to safely avoid moving obstacles is to regard them as static obstacles cycle by cycle and use a re-planning mechanism to react to these obstacles in real time. A more advanced approach is to assume moving obstacles will keep constant velocity and heading. However, the deficiency is that the assumption must be made that moving obstacles will keep constant velocity while driving along the road. None of these assumptions captures the fact that the host autonomous vehicle's movement will affect surrounding vehicles' behavior.
  • A proposed prediction and cost function-based (PCB) system and technique is described herein for autonomous freeway driving applications. The PCB framework is extended via a sampled-based approach to deal with sensor uncertainties and field-of-view constraints. The sample-based PCB algorithm is integrated with a Bayesian driving intention recognition model for the autonomous vehicle for performing social behavior. This intention-integrated Prediction-and Cost function-based (iPCB) system is implemented and tested in a simulated scenario of social cooperation with vehicles merging from freeway entrance ramps.
  • As shown in FIG. 1, there are four main subsystems in the iPCB system 10. The system includes a surrounding intention recognition estimation subsystem 12, a candidate strategy generation subsystem 14, an intention-based interactive prediction subsystem 16, a cost function-based strategy evaluation subsystem 18, and a controller in the autonomous driving system 20. It should be understood that each respective subsystem may utilize separate processors, controllers, and memory, or may share a processors, controllers, and memory.
  • The surrounding intention recognition estimation subsystem 12 captures the surrounding vehicle information input from the autonomous vehicle's perception system. The surrounding intention recognition subsystem uses a knowledge-based technique to output the probability of each surrounding vehicle's intention to the intention based interference prediction subsystem 16.
  • The candidate strategy generation subsystem 14 proposes a plurality of candidate driving strategies for the host vehicle to execute. The plurality of candidate driving strategies include sets of accelerations (i.e., positive accelerations) and/or decelerations (negative accelerations) applied by the host vehicle when encountering a vehicle merging into its lane. The intention-integrated prediction subsystem 16 uses the surrounding vehicles' intentions provided by the merging vehicle behavior recognition system 12 to predict the future traffic scenario assuming each of the candidate strategies is applied. The cost function-based evaluation subsystem 18 computes costs for each scenario and sums them together as the strategy cost. The autonomous driving system 20 selects the best strategy corresponding to the lowest cost and performs an autonomous merging maneuver.
  • To describe the operation of the iPCB system 10, a freeway entrance ramp management is selected which represents a difficult scenario where vehicles (autonomous or nonautonmous) need to exhibit social behavior, and the iPCB technique can be applied. For the entrance ramp management system, a scenario is shown in FIG. 2. A host vehicle 22 is driving in the rightmost lane of the freeway 24. Start point A of the entrance ramp is a location where the autonomous vehicle begins to consider the intentions of the merging vehicle 26. End point B is a location of the entrance ramp where there merging vehicle 26 fully merges in the rightmost lane of the freeway 24. Distances dA and dB are the longitudinal distances from a reference point O to points A and B. Point C in FIG. 2 is defined as the point at which the interaction between the two vehicles needs to be complete. The position of C and dC is computed using the following formula:

  • d c =d A+(d B −d A)/ωlane·(ωlane−ωcar  (1)
  • where ωlane is the width of the lane and ωcar is the width of the merging vehicle.
  • After point C, the vehicles should return to their normal lane driving and distance keeping mode. For the example described herein, all scenarios are implemented with parameters dA=40 m, dB=120 m, ωlane=6 m, ωcar=2 m.
  • In this embodiment, only the autonomous vehicle's single-lane driving performance is considered, which means the host vehicle 22 (autonomous vehicle) will keep performing lane centering in its current lane without changing to another lane. The host vehicle's function is to adjust speed by changing its acceleration ghost. The host vehicle's state is given by dhost, vhost and lhost where dhost and vhost are respectively the longitudinal distance and speed of the autonomous vehicle, and lhost is the lateral position of the host vehicle 22.
  • It is assumed that the merging vehicle 26 will merge along a fixed path corresponding to the center line of the entrance ramp. Similarly to the host vehicle, it has observable state dmerge, vmerge and lmerge obtainable from the perception system of the autonomous vehicle. In addition, to represent the autonomous vehicle's understanding of the merging vehicle's behavior, an intention state imerge is included which can be either Yield (Y) or Not Yield (NY).
  • For other remote vehicles, including vehicles in adjacent lanes and any vehicles leading or following the autonomous vehicle, parameters di, vi and li are used to represent other remote vehicle's longitudinal position, speed, and lateral distance.
  • A first step in the iPCB process framework is to generate a statistical model by estimating the merging vehicle intention I and use probability, p(I=Y) or p(Y) (i.e., the probability of the merging vehicle to yield) and p(I=N) or p(N) (i.e., the probability of the merging vehicle to not yield) to capture the uncertainty of the estimation. The intention recognition mechanism proposed herein referred to as the merging vehicle behavior recognition technique is based on Bayes' theorem as represented as follows:
  • p ( Y B ) = p ( B Y ) p ( Y ) / [ p ( Y ) p ( B Y ) + p ( N ) p ( B N ) ] = p ( B Y ) × 0.5 / [ 0.5 p ( B Y ) + 0.5 p ( B N ) ] = p ( B Y ) / [ p ( B Y ) + p ( B N ) ] ( 2 )
  • where p(Y|B) is the probability of merging vehicle's intention to yield (Y) given an observed behavior B, and p(B|Y) and p(B|N) are respectively the probabilities of that same behavior given intention Y or N. As no prior knowledge of the intention of the merging vehicle is available, the most difficult scenario is selected and the probability of yield p(Y) and not yield p(N) are both set to 0.5.
  • To estimate intent of the merging vehicle, the acceleration of the merging vehicle must be determined. The acceleration may be captured by sensing devices of the host vehicle or may be obtained through vehicle-to-vehicle communications between the host vehicle and the merging vehicle. A decelerating vehicle is more likely to intend to yield to host vehicle, and an accelerating vehicle less likely to yield to the host vehicle. Therefore, the acceleration is computed from the velocity measurement of the merging vehicle and is represented as follows:

  • acct(t)=(v(t)−v(t−t filter))  (3)
  • where v(t) is the observed merging vehicle velocity at time t and tfilter is the filtering horizon.
  • A merging vehicle behavior model B|I is generated representing the behavior B (acceleration or deceleration) expected from the merging vehicle given a particular intention I. If the merging vehicle intends to yield to the host vehicle, it will tend to merge into the lane of the host vehicle with a proper forward distance to the host vehicle. Otherwise, the merging vehicle will try to get ahead of the host vehicle and keep a reasonable backward distance when it enters the lane.
  • To generate the statistical model, a deterministic model is first generated and then the deterministic model is converted to a statistical model utilizing a Gaussian distribution. The deterministic model will provide a position and velocity of the merging vehicle from a kinematics point of view for identifying where the merging vehicle will be. FIG. 3 illustrates the freeway entrance ramp identifying key positions along the entrance ramp. Point C represents an end of the interaction region. Points Dyield and Dnyield are locations where the merging vehicle is supposed to be when the host vehicle arrives at C for the yield and not-yield cases, respectively. Equations for a deterministic model are as follows:

  • d yield =d C−(d min +k v v host)

  • d nyield =d C+(d min +k v v host)

  • Δt=(d yield,nyield −d merge)/v merge−(d C −d host)/v host

  • accmerge =c gain Δt  (4)
  • where dyield is the distance from C to Dyield, dnyield the distance from C to Dnyield dmin is the minimum desired distance to the leading vehicle, k is a gain causing the desired distance to grow with the host vehicle's speed, dmerge and dhost are the positions of the merging and host vehicles at any given instance of time. The desired control command for the merging vehicle accmerge is computed using a proportional controller applied to the difference between the arrival times of the merging vehicle and the autonomous vehicle, where Δt is the time difference between the two vehicles' arrivals at C, and cgain is the proportional gain converting the time difference into the acceleration command of the merging vehicle.
  • Simulation results are shown in FIGS. 4 a and 4 b. In FIG. 4 a, the merging vehicle is given an intention (I) of Yield, so it gradually applies deceleration and eventually merges into the main lane behind the host vehicle with the desired distance to the leader. Under this intention (I), the merging vehicle should try to reach Dyield when the host vehicle is at C. In FIG. 4 b, the merging vehicle is given an intention (I) of Not Yield, so merging vehicle accelerates to merge in front of the host vehicle. Under this intention (I), the merging vehicle should try to reach Dnyield when the host vehicle is at C. This model can emulate the behavior of a merging vehicle performing speed adjustment to enact its intention.
  • The following description utilizes a deterministic model of B|I for converting the model to a statistical (i.e., probabilistic) model. Although the deterministic model provides details as to the position and velocity of the merging vehicle, the deterministic model does not provide foresight as to the intentions of the merging vehicle. Therefore, by integrating intent with the deterministic model, the intentions of the merging model can be estimated with a respective confidence level. Under this scenario, the model is extended by superimposing a Gaussian distribution with its peak at the accmerge values for B|Y and B|N and standard deviation σ=0.8 m/s2, as shown in FIG. 5. B|Y represents the merging vehicle's intention to yield, whereas B|N represents the merging vehicle's intention to not yield. The graph shown in FIG. 5 gives exemplary probabilistic estimates p(B|Y) and p(B|N) of the merging vehicle acceleration given the two possible intentions and is used to capture the uncertainty-based deviation of the merging vehicle's behavior from the B|I model. It should be understood that other probabilistic distributions can be considered. By integrating p(B|I) with the Bayesian rule in Eq. 2, a merging vehicle intention probability estimator is produced. As a result, a social behavior of the merging vehicle can be quantified.
  • FIGS. 6 a and 6 b illustrate verification results implemented in simulation to verify the intention estimator's performance. The test parameters were provided that the merging vehicle was given a certain intention (I=Y or I=N) and followed the model B|I. The results of the real-time intention probability recognition are illustrated in FIG. 6 a. Corresponding scenarios are shown in FIG. 6 b. In FIG. 6 b, the vehicle begins to perform minor adjustment of its speed around t=4.0 s. FIG. 6 b also shows the corresponding scenarios at t=6.0 s. The intention estimator captures the initial behavior and outputs a probability of intention of the merging vehicle. The intention estimation results are very ambiguous at the beginning, but as the merging vehicle gets closer to point C around t=6.0 s, confidence of the estimation result increases rapidly.
  • Although the command for the autonomous vehicle in the freeway entrance ramp management system is an instantaneous velocity command, the host vehicle is attempting to identity an immediate and best available action based on the actions of the merging vehicle. The host vehicle also needs to consider a series of future control commands, (i.e., a velocity profile for the next tpredictLength in seconds). Due to the real-time requirement and limited computation power, only a limited number of strategies can be searched and evaluated. Therefore, a discretization of the strategy set is used.
  • FIG. 7 illustrates the discretization strategies of the host vehicle. The strategies include velocity profiles that are plotted as velocity (m/sec) over time (sec). Each of the strategies includes various combinations of positive acceleration and or negative accelerations that the host vehicle may utilize when encountering a vehicle merging within its lane. For example, the velocity provides may include a positive acceleration that changes to elevated acceleration, a negative acceleration that changes to a lower negative acceleration, a positive acceleration that changes to a negative acceleration, and a negative acceleration that changes to a positive acceleration.
  • Each velocity profile is represented by three parameters: tadjust, the total speed adjustment time, afirst which is the acceleration amplitude for the first half of tadjust, and asecond which is the acceleration amplitude for the second half of tadjust. The entire timeframe tpredictLength is chosen to be 10.0 seconds and is discretized into two values, 3.0 s or 5.0 s. There are 13 different acceleration options covering the range from −3.0 m/s2 to 2.0 m/s2. The candidate strategy generator outputs 378 strategies in all, which allows the iPCB algorithm to re-assess the host vehicle strategy in relation to the merging vehicle fast enough for the real-time implementation. As a result, the host vehicle can force a respective strategy in an attempt to illicit a respective intention of the merging vehicle.
  • After the candidate strategy generation, a prediction engine is used to simulate future scenarios for each strategy. For surrounding vehicles, including the leading or following vehicle of the autonomous car, the following prediction model:
  • Δ d 1 = d 1 - d v ( t ) a v ( t ) = { μ free ( v lim - v v ( t ) ) if Δ d i > 100 μ dk ( d d - d 1 ) + μ dkv ( v l - v v ( t ) ) if Δ d i < 100 } ( 5 )
  • where Δdi is the distance to vehicle vi's leader, μfree is the proportional gain for the vehicle to gradually approach the speed limit when there are no obstacles in front of it, μdk is the proportional gain of the distance keeping controller, and μdkv is the proportional gain on the velocity difference between the leader and the vehicle vi.
  • The intention of a merging vehicle from the intention recognition technique will be used to determine a more accurate prediction. The model as described earlier to generate B|I is used. The following steps are used with the B|I model. When the merging car's yield/not yield decision is obvious, the input/will be overridden, as identified in the following equation:
  • I = { Y , if Δ t > 3.0 N , if Δ t < 3.0 } ( 6 )
  • where Δt is computed using Eq. 4. For instance, if the merging vehicle is much slower than and far behind the host vehicle, it will surely yield to the host vehicle. In these cases, only one intention will be considered in prediction.
  • An important effect of this override mechanism is that even when a merging vehicle intention ambiguity exists at the beginning of the prediction, if the host vehicle performs a certain behavior, it has the ability to force the merging vehicle to converge to a predictable decision.
  • The interactive prediction module gives the iPCB framework the ability to predict how surrounding vehicles will react to the host vehicle's strategy, which is a key factor enabling the autonomous vehicle to socially interact with them. Compared with the prediction mechanism of other motion planning and distance keeping techniques, which is based on the assumption that surrounding vehicles will keep constant velocity and will not be affected by the host vehicle's behavior, the proposed prediction model is more accurate.
  • The prediction module generates a sequence of predicted scenarios from the current time t=0 to t=tpredictLength with constant time step Δt. Each entrance ramp scenario is represented by the longitudinal positions, speeds, and lateral positions of the host, merging and surrounding vehicles dhost,merge,i, vhost,merge,i, lhost,merge,i. A cost for each scenario Csce is then computed, which consists of four different cost functions. The four cost functions include, progress cost, comfort cost, safety cost, and fuel consumption cost.
  • The progress cost (Cprogress) represents how well a strategy does in finishing a given task by penalizing those strategies which take longer to finish the task. The goal of the distance keeper is to keep a desired distance ddesired to its leader, which is represented as follows by the following equation:

  • d desired =d min +k v v  (7)
  • where v is the current velocity of the vehicle, dmin is the distance to the leader when the vehicle is stationary, and kv is the gain of the desired distance increase corresponding to v.
  • Comfort cost (Ccomfort) represents scenarios when driving a vehicle, human drivers will generally try to avoid large accelerations for greater comfort.
  • The safety cost Csafety of a scenario consists of two terms: the clear distance cost Cdistance and the braking distance cost Cbrake. The clear distance cost Cdistance penalizes the host vehicle when it is moving too close to surrounding vehicles. However, this cost is not informative enough to avoid collision in some situations, since this factor does not consider the vehicles' relative velocities. Therefore, another safety cost based on the braking distance difference Δdbrake between two vehicles is also considered.
  • The fuel consumption cost Cfuel is proportional to the fuel usage as estimated by a comprehensive modal emission statistical model.
  • The parameters of these cost functions are selected based on case tests and statistical tests in a simulator with simulated traffic vehicles. The total cost of a scenario is the weighted sum of all these costs and is represented by the following formula:

  • C sce1 C progress2 C comfort3 C safety4 C fuel  (8)
  • where μ1, μ2, μ3, and μ4 represent a weight factor. That is, various cost parameters may not be as important as others, and therefore, the equation may be forced to provide greater weight to those factors that are more important.
  • By summing the scenario costs together, the cost for the ith strategy for a given intention (I) is generated as follows:
  • C str ( i ) I = t = 0 t Predict ( C sce ( i , t ) I ( 9 )
  • where Csce(i,t) is a cost of an ith scenario for a respective time t, (I) is an intention, and tPredict is duration of time over which system will predict the respective scenario. For example, if short duration of time is selected (e.g., 5 seconds), then the initial results will be more accurate; however long estimations will be unknown. If a longer duration of time is selected (e.g., 10 seconds), then the system will predict long term results; however, inaccuracies may result, as changes, such as speed, may occur which may skew the cost estimation.
  • The following formula represents a cost for a respective strategy for a given set of probabilities of an intention (I) to yield and not yield. The formula is represented as follows:

  • C str(i) =p(I=Y)C str(i) |Y+p(I=N)C str(i) |N  (10)
  • where p(I=Y) is a probability of the merging vehicle yielding during the merging maneuver, p(I=Y)Cstr(i)|N is the cost associated to the host vehicle as a result of the merging vehicle yielding to the host vehicle, p(I=N) is a probability of the merging vehicle not yielding during the merging maneuver, and, p(I=N)Cstr(i)|N is the cost associated to the host vehicle as a result of the merging vehicle not yielding to the host vehicle.
  • To manage any uncertainty in the state variable I, a sample-based approach is used to compute the expectation of the strategy cost Cstr(i).
  • The best freeway entrance ramp management strategy is selected based on the lowest accumulated cost, which is computed using Eq. 10.
  • To verify the performance of the proposed iPCB framework for autonomous freeway driving entrance ramp management, case tests focused on qualitative analysis were implemented. FIGS. 8 a and 8 b show the speeds (host and merging) and lateral and longitudinal distances, respectively, between vehicles for the autonomous vehicle performing single-lane autonomous driving with three different algorithms. Since the adaptive cruise control system only considers vehicles in the same lane as the host vehicle, it does not react to the merging vehicle until it crosses the lane divider which causes emergency braking and an uncomfortably small distance between vehicles (5.2 m).
  • FIGS. 9 a and 9 b illustrate an extension (i.e., geoACC) of the basic ACC for better handling of merging vehicles. This approach includes geographical information such as the shape of the road and entrance ramp and some rules governing whether the autonomous vehicle should yield. If the merging vehicle arrives before the host vehicle, then the autonomous system will decide to yield, as indicated by the following equation:
  • D host = { N , if Δ t > 0 Y , if Δ t < 0 } ( 11 )
  • where dhost is the host vehicle decision, and Δt is determined using Eq. 4. If the host vehicle arrives before the merging vehicle, it will try get in front of the merging vehicle. Therefore, if the decision is Y (yield), then the autonomous vehicle will perform distance keeping on the merging vehicle while it is still on the entrance ramp. If it is N (not yield), it will ignore the vehicle on the ramp.
  • If the host and merging vehicles arrive at around the same time, these rules may result in oscillation between the yield and not yield decisions which results in a scenario difficult to handle by the geoACC. Another problematic case of the geoACC algorithm is when the merging vehicle wants to perform some social interaction with the host vehicle, which the host vehicle does not understand. This is indicated in FIGS. 9 a and 9 b. At the beginning, the host vehicle decides to yield to the merging vehicle because Δt≦0. However, the merging vehicle wants to yield to the host vehicle, as well. The result is that the merging vehicle decreases its speed, and the host vehicle applies distance keeping to it, further decreasing its speed. This social misunderstanding causes the host vehicle to brake very hard to keep a safe distance to the merging vehicle, but this causes a potentially dangerous situation on highways. For a human driver, as long as it is understood that the merging vehicle wants to yield, the host vehicle decision will switch from yield to not yield in most situations.
  • In contrast to these two approaches based on the current ACC system, the iPCB algorithm can actively perform a behavior that attempts to convey its preference to the merging vehicle in the social cooperation. For testing purposes, the most ambiguous scenario is created, in which the host and merging vehicles have the same longitudinal coordinate and speed, and the merging vehicle is told to have an intention to yield (I=Y). In the iPCB plots of FIGS. 10 a and 10 b, as soon as the merging vehicle performs an intentional behavior (deceleration to yield to the host vehicle), the host vehicle understands it and begins to accelerate slightly to clearly show the merging car its cooperative behavior. This makes the speed variation of both vehicles much smaller and the distance between vehicles when the merging vehicle cuts in very close to the desired distance keeping distance ddesired.
  • In summary, the iPCB technique described herein performs in the most reasonable and cooperative manner to interact with merging vehicles on entrance ramps. It increases the smoothness of the velocity adjustment and also keeps the distance between merging and autonomous vehicles in a safe range.
  • In test cases conducted herein, the iPCB algorithm's general ability to perform social behavior was verified. A statistical test was implemented in simulation to analyze its ability to deal with a wide variety of different entrance ramp management scenarios. The simulation for each algorithm was run 10,000 times to get a more accurate statistical result.
  • Table I illustrates exemplary parameters ranges utilized for these statistical tests.
  • Parameter Min Max dmerge (m) −60.0 20.0 vmerge (m/s) 5.0 15.0 imerge Y or N dhost (m) −60.0 20.0 vhost (m/s) 5.0 15.0

    Table II shows the result of this test, where Cave is the average strategy cost.
  • ACC geoACC iPCB Cave 52.25 56.61 30.58 Csafety 7.51 6.56 2.45 Cdk 20.73 20.55 21.94 Cacc 4.84 6.56 0.66 Ndanger 52 62 9

    Csafety, Cacc, Cdk are respectively the safety, comfort, and distance keeping progress cost. Ndanger is the number of cases in which the car needed to apply hard braking (with deceleration larger than 3 m/s2) to avoid an accident.
  • The iPCB algorithm clearly provides the lowest strategy cost, which indicates that the quality of the decision making at entrance ramps is improved. Compared with the ACC and geoACC approaches, the safety and acceleration costs are reduced considerably, meaning the control of the vehicle is smoother and safer. The number of potentially dangerous scenarios is also greatly reduced by using the iPCB algorithm due to its ability to react earlier to merging vehicles based on their intention. This test also verifies that the iPCB algorithm framework is beneficial across a wide range of entrance ramp scenarios.
  • Once the autonomous maneuver is selected that provides the lowest cost and greatest benefit for performing the merging maneuver, control signals are provided to one or more controllers for controlling the autonomous driving system for seamlessly merging with vehicles entering the freeway merging lane. For example, a vehicle speed controller may be used to control the speed of the vehicle to follow a selected strategy in an attempt to illicit a respective intention from the merging vehicle. The behavior of the merging vehicle is constantly monitored, and depending on the response of the merging vehicle, the current strategy for the identified intention may be continuously applied, or another strategy may be selected and the speed controller will react accordingly.
  • It should be understood that the embodiments described herein are not limited to high entrance ramps, but may also be applied to lane changes (using, for example, lateral and longitudinal accelerations) and other driving maneuvers that require a host vehicle to monitor surrounding vehicles and cooperatively allow a remote vehicle access to the host vehicle's lane.
  • While certain embodiments of the present invention have been described in detail, those familiar with the art to which this invention relates will recognize various alternative designs and embodiments for practicing the invention as defined by the following claims.

Claims (21)

1. An autonomous driving merge management system comprising:
an autonomous driving control device for autonomously controlling accelerations of a host vehicle;
an intention decision management system comprising:
a candidate strategy subsystem generating a plurality of candidate driving strategies, each candidate driving strategy being a potential driving strategy executable by the host vehicle;
a merging vehicle behavior recognition subsystem predicting a merging intention of a merging vehicle; the merging intention relating to a positive acceleration or a negative acceleration of the merging vehicle;
an intention-based interactive prediction subsystem predicting future merging scenarios between the host vehicle and merging vehicle as a function of inputs by the merging vehicle behavior recognition subsystem and inputs by the candidate strategy subsystem;
a cost function-based evaluation subsystem determining a cost for each future merging scenario generated by the intention-based interactive prediction subsystem; and
a processor for selecting a merge strategy of the host vehicle based on intention-based prediction results and cost function-based evaluation results;
wherein the autonomous driving control device applies the merge strategy to the host vehicle for allowing the merging vehicle to cooperatively merge with the host vehicle.
2. The autonomous driving merge management system of claim 1 wherein the cost function-based evaluation subsystem determines the cost for each scenario based on a progress cost, a comfort cost, a safety cost, and fuel consumption cost associated with a respective scenario.
3. The autonomous driving merge management system of claim 2 wherein the progress cost includes an efficiency of completing a task during a merging maneuver.
4. The autonomous driving merge management system of claim 2 wherein the comfort cost includes avoiding excessive accelerations of the vehicle to complete the merging maneuver.
5. The autonomous driving merge management system of claim 2 wherein the safety cost includes maintaining a respective distance to the merging vehicle and maintaining a braking distance based on the velocity of the host vehicle and merging vehicle.
6. The autonomous driving merge management system of claim 2 wherein the fuel consumption cost includes an amount of fuel expended to complete a merging maneuver.
7. The autonomous driving merge management system of claim 2 wherein the cost function-based evaluation subsystem determines the cost for a respective scenario based on the following formula:

C sce1 C progress2 C comfort3 C safety4 C fuel  (8)
where Cprogress is the progress cost, Ccomfort is the comfort cost, Csafety is the safety cost, Cfuel fuel consumption cost, and μ1, μ2, μ3, and μ4 represent weight factors.
8. The autonomous driving merge management system of claim 7 wherein a cost for a respective strategy for a respective intention is represented by the following formula:
C str ( i ) I = t = 0 t Predict ( C sce ( i , t ) I
where Csce(i,t) is a cost of an ith scenario for a respective time t, I is an intention, and tPredict is a duration of time over which system will predict the respective scenario.
9. The autonomous driving merge management system of claim 8 wherein a cost for a respective strategy given a respective probability of an intention is represented by the following formula:

C str(i) =p(I=Y)C str(i) |Y+p(I=N)C str(i) |N
where p(I=Y) is a probability of the remote vehicle yielding during the merging maneuver, p(I=Y)Cstr(i)|Y is the cost associated to the host vehicle given the probability as a result of the merging vehicle yielding to the host vehicle, p(I=N) is a probability of the merging vehicle not yielding during the merging maneuver, and p(I=N)Cstr(i)|N is the cost associated to the host vehicle given the probability as a result of the merging vehicle not yielding to the host vehicle.
10. The autonomous driving merge management system of claim 1 wherein the merging vehicle behavior recognition subsystem utilizes a statistical merging vehicle model for determining a vehicle behavior of the merging vehicle.
11. The autonomous driving merge management system of claim 1 wherein statistical merging vehicle model is represented by the following formula:
p ( Y B ) = p ( B Y ) p ( Y ) / [ p ( Y ) p ( B Y ) + p ( N ) p ( B N ) ] = p ( B Y ) × 0.5 / [ 0.5 p ( B Y ) + 0.5 p ( B N ) ] = p ( B Y ) / [ p ( B Y ) + p ( B N ) ]
where p(Y|B|) is the probability of merging vehicle's intention to yield (Y) given an observed behavior B, and p(B|Y) and p(B|N) are respectively probabilities of the same behavior given intention Y or N.
12. The autonomous driving merge management system of claim 10 wherein the statistical merging vehicle model is derived from a deterministic model utilizing a Gaussian distribution.
13. The autonomous driving merge management system of claim 10 wherein the statistical merging vehicle model is represented by the following equations:

d yield =d C−(d min +k v v host)

d nyield =d C+(d min +k v v host)

Δt=(d yield,nyield −d merge)/v merge−(d C −d host)/v host

accmerge =c gain Δt
where dyield is the distance from C to Dyield, dnyield the distance from C to Dnyield, dmin is the minimum desired distance to the leading vehicle, k is a gain causing the desired distance to grow with the host vehicle's speed, dmerge and dhost are the positions of the merging and host vehicles at any given instance of time, accmerge is a desired control command for the merging vehicle, Δt is a time difference between the host vehicle and merging vehicle arrivals at C, and cgain is the proportional gain converting the time difference into the acceleration command of the merging vehicle.
14. The autonomous driving merge management system of claim 1 wherein the autonomous driving control device includes a speed controller device.
15. The autonomous driving merge management system of claim 1 wherein the intention decision management system determines an intention of the merging vehicle to merge relative to the host vehicle when transitioning from an entrance ramp to a primary driven road traveled by the host vehicle.
16. The autonomous driving merge management system of claim 1 wherein the intention decision management system determines an intention of the merging vehicle relative to the host vehicle when changing lanes from an adjacent lane to a primary driven lane of the host vehicle.
17. A method for autonomously controlling a vehicle speed during a merging maneuver between a host vehicle and a merging vehicle, the method comprising the steps of:
obtaining speed data and position data of the host vehicle and the remote data;
generating a plurality of candidate driving strategies by a processor, each candidate driving strategy being a potential driving strategy executable by the host vehicle;
predicting an intention of the merging vehicle to merge forward or rearward of the host vehicle by the processor,
generating a plurality of merging scenarios between the host vehicle and merging vehicle by the processor as a function of the predicted merging intention of the merging vehicle and the plurality of candidate driving strategies;
determining a cost for each merging scenario by the processor based on a cost function evaluation analysis technique;
selecting a merge strategy of the host vehicle by the processor based on the cost function evaluation results; and
autonomously controlling accelerations of a host vehicle using an autonomous driving control device, wherein the autonomous driving control device applies the merge strategy to the host vehicle for cooperatively allowing the merging vehicle to cooperatively merge with the host vehicle.
18. The method of claim 17 wherein processor determines the cost for each scenario based on a progress cost, a comfort cost, a safety cost, and fuel consumption cost associated with a respective scenario.
19. The method of claim 18 wherein the processor determines the cost for a respective scenario based on the following formula:

C sce1 C progress2 C comfort3 C safety4 C fuel  (8)
where Cprogress is the progress cost, Ccomfort is the comfort cost, Csafety is the safety cost, Cfuel fuel consumption cost, and μ1, μ2, μ3, and μ4 represent weight factors.
20. The method of claim 19 wherein a cost for a respective strategy for a respective intention is represented by the following formula:
C str ( i ) I = t = 0 t Predict ( C sce ( i , t ) I
where Csce(i,t) is a cost of an ith scenario for a respective time t, I is an intention, and tPredict is a duration of time over which system will predict the respective scenario.
21. The method of claim 20 wherein a cost for a respective strategy given a respective probability of an intention is represented by the following formula:

C str(i) =p(I=Y)C str(i) |Y+p(I=N)C str(i) |N
where p(I=Y) is a probability of the remote vehicle yielding during the merging maneuver, p(I=Y)Cstr(i)|Y is the cost associated to the host vehicle given the probability as a result of the merging vehicle yielding to the host vehicle, p(I=N) is a probability of the merging vehicle not yielding during the merging maneuver, and p(I=N)Cstr(i)|N is the cost associated to the host vehicle given the probability as a result of the merging vehicle not yielding to the host vehicle.
US13/733,919 2013-01-04 2013-01-04 Autonomous driving merge management system Active US8788134B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US13/733,919 US8788134B1 (en) 2013-01-04 2013-01-04 Autonomous driving merge management system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US13/733,919 US8788134B1 (en) 2013-01-04 2013-01-04 Autonomous driving merge management system

Publications (2)

Publication Number Publication Date
US20140195093A1 true US20140195093A1 (en) 2014-07-10
US8788134B1 US8788134B1 (en) 2014-07-22

Family

ID=51061609

Family Applications (1)

Application Number Title Priority Date Filing Date
US13/733,919 Active US8788134B1 (en) 2013-01-04 2013-01-04 Autonomous driving merge management system

Country Status (1)

Country Link
US (1) US8788134B1 (en)

Cited By (38)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140195214A1 (en) * 2013-01-10 2014-07-10 International Business Machines Corporation Automatic driver modeling for integration of human-controlled vehicles into an autonomous vehicle network
JP2016134115A (en) * 2015-01-22 2016-07-25 トヨタ自動車株式会社 Joining assist system
US9443153B1 (en) * 2015-06-12 2016-09-13 Volkswagen Ag Automatic labeling and learning of driver yield intention
CN106203727A (en) * 2016-07-19 2016-12-07 江苏大学 A kind of road traffic accident chain risk real time evaluating method
US20170147005A1 (en) * 2015-11-19 2017-05-25 Agjunction Llc Automated multi-vehicle alignment steering
WO2017091690A1 (en) * 2015-11-26 2017-06-01 Gideon Stein Automatic prediction and altruistic response to a vehicel cutting in a lane
WO2017210222A1 (en) * 2016-05-30 2017-12-07 Faraday&Future Inc. Generating and fusing traffic scenarios for automated driving systems
US9873429B1 (en) 2016-07-08 2018-01-23 Volkswagen Ag Turned-wheel detection for yielding during low-speed lane changes
US9884630B1 (en) * 2016-07-05 2018-02-06 Uber Technologies, Inc. Autonomous vehicle performance optimization system
US9892296B2 (en) 2014-11-12 2018-02-13 Joseph E. Kovarik Method and system for autonomous vehicles
US20180061236A1 (en) * 2015-03-18 2018-03-01 Nec Corporation Driving control device, driving control method, and vehicle-to-vehicle communication system
US9928746B1 (en) 2016-09-16 2018-03-27 Ford Global Technologies, Llc Vehicle-to-vehicle cooperation to marshal traffic
CN108137006A (en) * 2016-09-28 2018-06-08 百度(美国)有限责任公司 For the system delay Corrective control method of automatic driving vehicle
US10017180B2 (en) * 2015-10-28 2018-07-10 Honda Motor Co., Ltd. Vehicle control apparatus, vehicle control method, and vehicle control program
US10037696B2 (en) * 2016-03-31 2018-07-31 Delphi Technologies, Inc. Cooperative automated vehicle system
US10062288B2 (en) * 2016-07-29 2018-08-28 GM Global Technology Operations LLC Systems and methods for autonomous driving merging management
US10126136B2 (en) 2016-06-14 2018-11-13 nuTonomy Inc. Route planning for an autonomous vehicle
US20180341269A1 (en) * 2017-05-24 2018-11-29 Qualcomm Incorporated Holistic planning with multiple intentions for self-driving cars
US10152882B2 (en) 2015-11-30 2018-12-11 Nissan North America, Inc. Host vehicle operation using remote vehicle intention prediction
US10160317B2 (en) * 2015-05-29 2018-12-25 Toyota Jidosha Kabushiki Kaisha Vehicle speed control apparatus and vehicle speed limiting apparatus
US10168705B2 (en) * 2017-04-06 2019-01-01 Uber Technologies, Inc. Automatic tuning of autonomous vehicle cost functions based on human driving data
US20190126919A1 (en) * 2017-10-30 2019-05-02 Wipro Limited System and method for navigating an autonomous vehicle
US10304333B2 (en) * 2015-11-04 2019-05-28 Volkswagen Aktiengesellschaft Method and vehicle communication system for determining a driving intention for a vehicle
US10309792B2 (en) 2016-06-14 2019-06-04 nuTonomy Inc. Route planning for an autonomous vehicle
US10331129B2 (en) 2016-10-20 2019-06-25 nuTonomy Inc. Identifying a stopping place for an autonomous vehicle
WO2019132930A1 (en) * 2017-12-28 2019-07-04 Intel Corporation System and method for simulation of autonomous vehicles
US10427672B2 (en) * 2012-05-14 2019-10-01 Waymo Llc Consideration of risks in active sensing for an autonomous vehicle
US20190329783A1 (en) * 2017-01-12 2019-10-31 Mobileye Vision Technologies Ltd. Navigation at alternating merge zones
US10466701B2 (en) * 2016-12-06 2019-11-05 Toyota Jidosha Kabushiki Kaisha Autonomous driving system
US10473470B2 (en) 2016-10-20 2019-11-12 nuTonomy Inc. Identifying a stopping place for an autonomous vehicle
US20190375400A1 (en) * 2018-06-08 2019-12-12 Denso International America, Inc. Collision avoidance systems and methods
US10627816B1 (en) * 2014-08-29 2020-04-21 Waymo Llc Change detection using curve alignment
EP3650297A1 (en) * 2018-11-08 2020-05-13 Bayerische Motoren Werke Aktiengesellschaft Method and apparatus for determining information related to a lane change of a target vehicle, method and apparatus for determining a vehicle comfort metric for a prediction of a driving maneuver of a target vehicle and computer program
US10681513B2 (en) 2016-10-20 2020-06-09 nuTonomy Inc. Identifying a stopping place for an autonomous vehicle
US10739782B2 (en) * 2016-10-31 2020-08-11 Mobileye Vision Technologies Ltd. Systems and methods for navigating lane merges and lane splits
US10857994B2 (en) 2016-10-20 2020-12-08 Motional Ad Llc Identifying a stopping place for an autonomous vehicle
US10902725B2 (en) * 2016-03-25 2021-01-26 Hitachi Automotive Systems, Ltd. Vehicle control device
US10909866B2 (en) 2018-07-20 2021-02-02 Cybernet Systems Corp. Autonomous transportation system and methods

Families Citing this family (75)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106030609B (en) 2013-12-04 2020-07-03 移动眼视力科技有限公司 System and method for simulating a leading vehicle
US10422649B2 (en) * 2014-02-24 2019-09-24 Ford Global Technologies, Llc Autonomous driving sensing system and method
US9616888B2 (en) 2014-12-08 2017-04-11 Ford Global Technologies, Llc Vehicle speed adjustment
US10613544B2 (en) 2015-05-05 2020-04-07 B. G. Negev Technologies And Applications Ltd. Universal autonomous robotic driving system
US9639537B2 (en) 2015-06-19 2017-05-02 International Business Machines Corporation Geographic space management
US10019446B2 (en) 2015-06-19 2018-07-10 International Business Machines Corporation Geographic space management
US9934688B2 (en) 2015-07-31 2018-04-03 Ford Global Technologies, Llc Vehicle trajectory determination
US9864918B2 (en) 2015-11-04 2018-01-09 Ford Global Technologies, Llc Predicting vehicle movements based on driver body language
US9983591B2 (en) 2015-11-05 2018-05-29 Ford Global Technologies, Llc Autonomous driving at intersections based on perception data
US9865163B2 (en) 2015-12-16 2018-01-09 International Business Machines Corporation Management of mobile objects
US9805598B2 (en) * 2015-12-16 2017-10-31 International Business Machines Corporation Management of mobile objects
US10625742B2 (en) 2016-06-23 2020-04-21 Honda Motor Co., Ltd. System and method for vehicle control in tailgating situations
US10737667B2 (en) 2016-06-23 2020-08-11 Honda Motor Co., Ltd. System and method for vehicle control in tailgating situations
US10081357B2 (en) 2016-06-23 2018-09-25 Honda Motor Co., Ltd. Vehicular communications network and methods of use and manufacture thereof
US10286913B2 (en) 2016-06-23 2019-05-14 Honda Motor Co., Ltd. System and method for merge assist using vehicular communication
US10449962B2 (en) 2016-06-23 2019-10-22 Honda Motor Co., Ltd. System and method for vehicle control using vehicular communication
US10496091B1 (en) 2016-08-17 2019-12-03 Waymo Llc Behavior and intent estimations of road users for autonomous vehicles
US10640111B1 (en) 2016-09-07 2020-05-05 Waymo Llc Speed planning for autonomous vehicles
US10399564B2 (en) 2016-10-25 2019-09-03 Ford Global Technologies, Llc Vehicle roundabout management
US10332403B2 (en) 2017-01-04 2019-06-25 Honda Motor Co., Ltd. System and method for vehicle congestion estimation
US10223598B2 (en) 2017-02-20 2019-03-05 Volkswagen Aktiengesellschaft Method of generating segmented vehicle image data, corresponding system, and vehicle
US10311312B2 (en) 2017-08-31 2019-06-04 TuSimple System and method for vehicle occlusion detection
US10783381B2 (en) 2017-08-31 2020-09-22 Tusimple, Inc. System and method for vehicle occlusion detection
US10147193B2 (en) 2017-03-10 2018-12-04 TuSimple System and method for semantic segmentation using hybrid dilated convolution (HDC)
US9953236B1 (en) 2017-03-10 2018-04-24 TuSimple System and method for semantic segmentation using dense upsampling convolution (DUC)
US10671873B2 (en) 2017-03-10 2020-06-02 Tusimple, Inc. System and method for vehicle wheel detection
US9952594B1 (en) 2017-04-07 2018-04-24 TuSimple System and method for traffic data collection using unmanned aerial vehicles (UAVs)
US10710592B2 (en) 2017-04-07 2020-07-14 Tusimple, Inc. System and method for path planning of autonomous vehicles based on gradient
US10471963B2 (en) 2017-04-07 2019-11-12 TuSimple System and method for transitioning between an autonomous and manual driving mode based on detection of a drivers capacity to control a vehicle
US10552691B2 (en) 2017-04-25 2020-02-04 TuSimple System and method for vehicle position and velocity estimation based on camera and lidar data
US10481044B2 (en) 2017-05-18 2019-11-19 TuSimple Perception simulation for improved autonomous vehicle control
US10558864B2 (en) 2017-05-18 2020-02-11 TuSimple System and method for image localization based on semantic segmentation
CN108932462A (en) * 2017-05-27 2018-12-04 华为技术有限公司 Driving intention determines method and device
US10474790B2 (en) 2017-06-02 2019-11-12 TuSimple Large scale distributed simulation for realistic multiple-agent interactive environments
US10762635B2 (en) 2017-06-14 2020-09-01 Tusimple, Inc. System and method for actively selecting and labeling images for semantic segmentation
US10752246B2 (en) 2017-07-01 2020-08-25 Tusimple, Inc. System and method for adaptive cruise control with proximate vehicle detection
US10303522B2 (en) 2017-07-01 2019-05-28 TuSimple System and method for distributed graphics processing unit (GPU) computation
US10737695B2 (en) 2017-07-01 2020-08-11 Tusimple, Inc. System and method for adaptive cruise control for low speed following
US10493988B2 (en) 2017-07-01 2019-12-03 TuSimple System and method for adaptive cruise control for defensive driving
US10308242B2 (en) 2017-07-01 2019-06-04 TuSimple System and method for using human driving patterns to detect and correct abnormal driving behaviors of autonomous vehicles
CN107416754B (en) 2017-07-21 2018-11-02 北京图森未来科技有限公司 A kind of automatic oiling methods, devices and systems of long-distance vehicle
CN107393074B (en) 2017-07-21 2019-01-18 北京图森未来科技有限公司 Realize the automatic method and system for crossing card of vehicle, relevant device
US10360257B2 (en) 2017-08-08 2019-07-23 TuSimple System and method for image annotation
US10816354B2 (en) 2017-08-22 2020-10-27 Tusimple, Inc. Verification module system and method for motion-based lane detection with multiple sensors
US10303956B2 (en) 2017-08-23 2019-05-28 TuSimple System and method for using triplet loss for proposal free instance-wise semantic segmentation for lane detection
US10762673B2 (en) 2017-08-23 2020-09-01 Tusimple, Inc. 3D submap reconstruction system and method for centimeter precision localization using camera-based submap and LiDAR-based global map
US10678234B2 (en) 2017-08-24 2020-06-09 Tusimple, Inc. System and method for autonomous vehicle control to minimize energy cost
US10782693B2 (en) 2017-09-07 2020-09-22 Tusimple, Inc. Prediction-based system and method for trajectory planning of autonomous vehicles
US10656644B2 (en) 2017-09-07 2020-05-19 Tusimple, Inc. System and method for using human driving patterns to manage speed control for autonomous vehicles
US10782694B2 (en) 2017-09-07 2020-09-22 Tusimple, Inc. Prediction-based system and method for trajectory planning of autonomous vehicles
US10649458B2 (en) 2017-09-07 2020-05-12 Tusimple, Inc. Data-driven prediction-based system and method for trajectory planning of autonomous vehicles
US10552979B2 (en) 2017-09-13 2020-02-04 TuSimple Output of a neural network method for deep odometry assisted by static scene optical flow
US10671083B2 (en) 2017-09-13 2020-06-02 Tusimple, Inc. Neural network architecture system for deep odometry assisted by static scene optical flow
US10733465B2 (en) 2017-09-20 2020-08-04 Tusimple, Inc. System and method for vehicle taillight state recognition
US10387736B2 (en) 2017-09-20 2019-08-20 TuSimple System and method for detecting taillight signals of a vehicle
US10768626B2 (en) 2017-09-30 2020-09-08 Tusimple, Inc. System and method for providing multiple agents for decision making, trajectory planning, and control for autonomous vehicles
US10410055B2 (en) 2017-10-05 2019-09-10 TuSimple System and method for aerial video traffic analysis
US10019011B1 (en) 2017-10-09 2018-07-10 Uber Technologies, Inc. Autonomous vehicles featuring machine-learned yield model
US10739775B2 (en) 2017-10-28 2020-08-11 Tusimple, Inc. System and method for real world autonomous vehicle trajectory simulation
US10666730B2 (en) 2017-10-28 2020-05-26 Tusimple, Inc. Storage architecture for heterogeneous multimedia data
US10812589B2 (en) 2017-10-28 2020-10-20 Tusimple, Inc. Storage architecture for heterogeneous multimedia data
US10627825B2 (en) 2017-11-22 2020-04-21 Waymo Llc Using discomfort for speed planning in autonomous vehicles
US10528823B2 (en) 2017-11-27 2020-01-07 TuSimple System and method for large-scale lane marking detection using multimodal sensor data
US10657390B2 (en) 2017-11-27 2020-05-19 Tusimple, Inc. System and method for large-scale lane marking detection using multimodal sensor data
US10528851B2 (en) 2017-11-27 2020-01-07 TuSimple System and method for drivable road surface representation generation using multimodal sensor data
US10877476B2 (en) 2017-11-30 2020-12-29 Tusimple, Inc. Autonomous vehicle simulation system for analyzing motion planners
US10860018B2 (en) 2017-11-30 2020-12-08 Tusimple, Inc. System and method for generating simulated vehicles with configured behaviors for analyzing autonomous vehicle motion planners
US10730521B2 (en) 2017-12-21 2020-08-04 Denso International America, Inc. System for autonomous lane merging
US10685244B2 (en) 2018-02-27 2020-06-16 Tusimple, Inc. System and method for online real-time multi-object tracking
US10685239B2 (en) 2018-03-18 2020-06-16 Tusimple, Inc. System and method for lateral vehicle detection
US10884410B2 (en) * 2018-06-29 2021-01-05 Toyota Motor Engineering & Manufacturing North America, Inc. Systems and methods for determining whether a vehicle is capable of navigating an intersection in an autonomous driving mode
US10839234B2 (en) 2018-09-12 2020-11-17 Tusimple, Inc. System and method for three-dimensional (3D) object detection
US10796402B2 (en) 2018-10-19 2020-10-06 Tusimple, Inc. System and method for fisheye image processing
US10752253B1 (en) * 2019-08-28 2020-08-25 Ford Global Technologies, Llc Driver awareness detection system
US10906558B1 (en) 2020-06-18 2021-02-02 Ike Robotics, Inc. Methods and systems for managing interactions of an autonomous vehicle with other objects

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5068654A (en) * 1989-07-03 1991-11-26 Hazard Detection Systems Collision avoidance system
US5554982A (en) * 1994-08-01 1996-09-10 Hughes Aircraft Co. Wireless train proximity alert system
US6232887B1 (en) * 1998-04-29 2001-05-15 Joseph E. Carson Warning systems
US6882287B2 (en) * 2001-07-31 2005-04-19 Donnelly Corporation Automotive lane change aid
US7102496B1 (en) * 2002-07-30 2006-09-05 Yazaki North America, Inc. Multi-sensor integration for a vehicle
JP3925474B2 (en) * 2003-07-18 2007-06-06 日産自動車株式会社 Lane change support device
JP4367431B2 (en) * 2005-10-26 2009-11-18 トヨタ自動車株式会社 Vehicle driving support system
US8452535B2 (en) * 2010-12-13 2013-05-28 GM Global Technology Operations LLC Systems and methods for precise sub-lane vehicle positioning
WO2012089357A2 (en) * 2010-12-29 2012-07-05 Siemens S.A.S. System and method for active lane-changing assistance for a motor vehicle
EP2562060B1 (en) * 2011-08-22 2014-10-01 Honda Research Institute Europe GmbH A method and system for predicting movement behavior of a target traffic object
US8810431B2 (en) * 2011-10-20 2014-08-19 GM Global Technology Operations LLC Highway merge assistant and control
US9771070B2 (en) * 2011-12-09 2017-09-26 GM Global Technology Operations LLC Method and system for controlling a host vehicle
US8706417B2 (en) * 2012-07-30 2014-04-22 GM Global Technology Operations LLC Anchor lane selection method using navigation input in road change scenarios

Cited By (51)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10427672B2 (en) * 2012-05-14 2019-10-01 Waymo Llc Consideration of risks in active sensing for an autonomous vehicle
US20140195214A1 (en) * 2013-01-10 2014-07-10 International Business Machines Corporation Automatic driver modeling for integration of human-controlled vehicles into an autonomous vehicle network
US9576083B2 (en) * 2013-01-10 2017-02-21 International Business Machines Corporation Automatic driver modeling for integration of human-controlled vehicles into an autonomous vehicle network
US10627816B1 (en) * 2014-08-29 2020-04-21 Waymo Llc Change detection using curve alignment
US10078770B2 (en) 2014-11-12 2018-09-18 Joseph E. Kovarik Method and system for autonomous vehicles
US10867139B2 (en) 2014-11-12 2020-12-15 Joseph E. Kovarik Method and system for autonomous vehicles
US9892296B2 (en) 2014-11-12 2018-02-13 Joseph E. Kovarik Method and system for autonomous vehicles
JP2016134115A (en) * 2015-01-22 2016-07-25 トヨタ自動車株式会社 Joining assist system
US10621869B2 (en) * 2015-03-18 2020-04-14 Nec Corporation Driving control device, driving control method, and vehicle-to-vehicle communication system
US20180061236A1 (en) * 2015-03-18 2018-03-01 Nec Corporation Driving control device, driving control method, and vehicle-to-vehicle communication system
US10160317B2 (en) * 2015-05-29 2018-12-25 Toyota Jidosha Kabushiki Kaisha Vehicle speed control apparatus and vehicle speed limiting apparatus
US9443153B1 (en) * 2015-06-12 2016-09-13 Volkswagen Ag Automatic labeling and learning of driver yield intention
US10017180B2 (en) * 2015-10-28 2018-07-10 Honda Motor Co., Ltd. Vehicle control apparatus, vehicle control method, and vehicle control program
US10304333B2 (en) * 2015-11-04 2019-05-28 Volkswagen Aktiengesellschaft Method and vehicle communication system for determining a driving intention for a vehicle
US20170147005A1 (en) * 2015-11-19 2017-05-25 Agjunction Llc Automated multi-vehicle alignment steering
US20170154225A1 (en) * 2015-11-26 2017-06-01 Mobileye Vision Technologies Ltd. Predicting and Responding to Cut In Vehicles and Altruistic Responses
US10209712B2 (en) 2015-11-26 2019-02-19 Mobileye Vision Technologies Ltd. Predicting and responding to cut in vehicles and altruistic responses
US10452069B2 (en) * 2015-11-26 2019-10-22 Mobileye Vision Technologies, Ltd. Predicting and responding to cut in vehicles and altruistic responses
WO2017091690A1 (en) * 2015-11-26 2017-06-01 Gideon Stein Automatic prediction and altruistic response to a vehicel cutting in a lane
EP3742338A1 (en) * 2015-11-26 2020-11-25 Mobileye Vision Technologies Ltd. Automatic prediction and altruistic response to a vehicle cutting in a lane
US10152882B2 (en) 2015-11-30 2018-12-11 Nissan North America, Inc. Host vehicle operation using remote vehicle intention prediction
US10902725B2 (en) * 2016-03-25 2021-01-26 Hitachi Automotive Systems, Ltd. Vehicle control device
CN108883767A (en) * 2016-03-31 2018-11-23 德尔福技术有限公司 Cooperate automated vehicle system
US10037696B2 (en) * 2016-03-31 2018-07-31 Delphi Technologies, Inc. Cooperative automated vehicle system
WO2017210222A1 (en) * 2016-05-30 2017-12-07 Faraday&Future Inc. Generating and fusing traffic scenarios for automated driving systems
US10309792B2 (en) 2016-06-14 2019-06-04 nuTonomy Inc. Route planning for an autonomous vehicle
US10126136B2 (en) 2016-06-14 2018-11-13 nuTonomy Inc. Route planning for an autonomous vehicle
US9884630B1 (en) * 2016-07-05 2018-02-06 Uber Technologies, Inc. Autonomous vehicle performance optimization system
US10392025B2 (en) 2016-07-05 2019-08-27 Uber Technologies Inc. Autonomous vehicle performance optimization system
US9873429B1 (en) 2016-07-08 2018-01-23 Volkswagen Ag Turned-wheel detection for yielding during low-speed lane changes
CN106203727A (en) * 2016-07-19 2016-12-07 江苏大学 A kind of road traffic accident chain risk real time evaluating method
US10062288B2 (en) * 2016-07-29 2018-08-28 GM Global Technology Operations LLC Systems and methods for autonomous driving merging management
US9928746B1 (en) 2016-09-16 2018-03-27 Ford Global Technologies, Llc Vehicle-to-vehicle cooperation to marshal traffic
CN108137006A (en) * 2016-09-28 2018-06-08 百度(美国)有限责任公司 For the system delay Corrective control method of automatic driving vehicle
US10857994B2 (en) 2016-10-20 2020-12-08 Motional Ad Llc Identifying a stopping place for an autonomous vehicle
US10681513B2 (en) 2016-10-20 2020-06-09 nuTonomy Inc. Identifying a stopping place for an autonomous vehicle
US10331129B2 (en) 2016-10-20 2019-06-25 nuTonomy Inc. Identifying a stopping place for an autonomous vehicle
US10473470B2 (en) 2016-10-20 2019-11-12 nuTonomy Inc. Identifying a stopping place for an autonomous vehicle
US10739782B2 (en) * 2016-10-31 2020-08-11 Mobileye Vision Technologies Ltd. Systems and methods for navigating lane merges and lane splits
US10466701B2 (en) * 2016-12-06 2019-11-05 Toyota Jidosha Kabushiki Kaisha Autonomous driving system
US20190329783A1 (en) * 2017-01-12 2019-10-31 Mobileye Vision Technologies Ltd. Navigation at alternating merge zones
US10168705B2 (en) * 2017-04-06 2019-01-01 Uber Technologies, Inc. Automatic tuning of autonomous vehicle cost functions based on human driving data
US10591920B2 (en) * 2017-05-24 2020-03-17 Qualcomm Incorporated Holistic planning with multiple intentions for self-driving cars
US20180341269A1 (en) * 2017-05-24 2018-11-29 Qualcomm Incorporated Holistic planning with multiple intentions for self-driving cars
US10449959B2 (en) * 2017-10-30 2019-10-22 Wipro Limited System and method for navigating an autonomous vehicle
US20190126919A1 (en) * 2017-10-30 2019-05-02 Wipro Limited System and method for navigating an autonomous vehicle
WO2019132930A1 (en) * 2017-12-28 2019-07-04 Intel Corporation System and method for simulation of autonomous vehicles
US10745007B2 (en) * 2018-06-08 2020-08-18 Denso International America, Inc. Collision avoidance systems and methods
US20190375400A1 (en) * 2018-06-08 2019-12-12 Denso International America, Inc. Collision avoidance systems and methods
US10909866B2 (en) 2018-07-20 2021-02-02 Cybernet Systems Corp. Autonomous transportation system and methods
EP3650297A1 (en) * 2018-11-08 2020-05-13 Bayerische Motoren Werke Aktiengesellschaft Method and apparatus for determining information related to a lane change of a target vehicle, method and apparatus for determining a vehicle comfort metric for a prediction of a driving maneuver of a target vehicle and computer program

Also Published As

Publication number Publication date
US8788134B1 (en) 2014-07-22

Similar Documents

Publication Publication Date Title
Bevly et al. Lane change and merge maneuvers for connected and automated vehicles: A survey
US20190329783A1 (en) Navigation at alternating merge zones
Li et al. Game theoretic modeling of driver and vehicle interactions for verification and validation of autonomous vehicle control systems
US20190107840A1 (en) Autonomous Vehicles Featuring Machine-Learned Yield Model
Zhou et al. On the impact of cooperative autonomous vehicles in improving freeway merging: a modified intelligent driver model-based approach
Althoff et al. Online verification of automated road vehicles using reachability analysis
Yang et al. Eco-cooperative adaptive cruise control at signalized intersections considering queue effects
Shalev-Shwartz et al. On a formal model of safe and scalable self-driving cars
KR20190028365A (en) Facilitating vehicle driving and unattended driving
Wang et al. Cooperative car-following control: Distributed algorithm and impact on moving jam features
JP6650214B2 (en) Method and system for post-collision maneuver planning, and vehicle equipped with the system
Wang et al. Game theoretic approach for predictive lane-changing and car-following control
Yu et al. A human-like game theory-based controller for automatic lane changing
EP3091370B1 (en) Method and arrangement for determining safe vehicle trajectories
US10843690B2 (en) Systems and methods for navigating a vehicle
Schildbach et al. Scenario model predictive control for lane change assistance on highways
KR20190091366A (en) Navigation system with imposed liability restrictions
Nilsson et al. If, when, and how to perform lane change maneuvers on highways
Houenou et al. Vehicle trajectory prediction based on motion model and maneuver recognition
JP6207723B2 (en) Collision prevention device
JP6232004B2 (en) Method for performing risk-based traffic scene analysis by advanced driver assistance system, and vehicle equipped with the system for performing the analysis
US8948995B2 (en) Preceding vehicle state prediction
Song et al. Intention-aware autonomous driving decision-making in an uncontrolled intersection
Baskar et al. Traffic management for automated highway systems using model-based predictive control
Zohdy et al. Intersection management for autonomous vehicles using iCACC

Legal Events

Date Code Title Description
AS Assignment

Owner name: GM GLOBAL TECHNOLOGY OPERATIONS LLC, MICHIGAN

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:LITKOUHI, BAKHTIAR BRIAN;WEI, JUNQING;DOLAN, JOHN M.;REEL/FRAME:029578/0731

Effective date: 20130103

Owner name: CARNEGIE MELLON UNIVERSITY, PENNSYLVANIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:LITKOUHI, BAKHTIAR BRIAN;WEI, JUNQING;DOLAN, JOHN M.;REEL/FRAME:029578/0731

Effective date: 20130103

AS Assignment

Owner name: WILMINGTON TRUST COMPANY, DELAWARE

Free format text: SECURITY INTEREST;ASSIGNOR:GM GLOBAL TECHNOLOGY OPERATIONS LLC;REEL/FRAME:033135/0336

Effective date: 20101027

STCF Information on status: patent grant

Free format text: PATENTED CASE

AS Assignment

Owner name: GM GLOBAL TECHNOLOGY OPERATIONS LLC, MICHIGAN

Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:WILMINGTON TRUST COMPANY;REEL/FRAME:034189/0065

Effective date: 20141017

MAFP Maintenance fee payment

Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551)

Year of fee payment: 4