Classifications

• • G—PHYSICS
  • G01—MEASURING; TESTING
  • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
  • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
  • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
  • G01C21/34—Route searching; Route guidance
  • G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
• • G—PHYSICS
  • G05—CONTROLLING; REGULATING
  • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
  • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
  • G05D1/02—Control of position or course in two dimensions
  • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
  • G05D1/0287—Control of position or course in two dimensions specially adapted to land vehicles involving a plurality of land vehicles, e.g. fleet or convoy travelling
  • G05D1/0289—Control of position or course in two dimensions specially adapted to land vehicles involving a plurality of land vehicles, e.g. fleet or convoy travelling with means for avoiding collisions between vehicles

Definitions

• the present invention relates to a system and method for managing a plurality of vehicles, particularly for transportation of objects in a manufacturing and/or logistics facility.
• Autonomous mobile vehicles are increasingly being put into service in the next phase of the industrial evolution, whereby the vehicles are configured to navigate autonomously to their intended destinations to carry out desired tasks.
• This increased adoption of autonomous mobile vehicles is driven by explosive growth in the global supply chain, and a drive to increase yield/productivity using automation.
• the vehicles When using a fleet of autonomous mobile vehicles, it is typical for the vehicles to be configured in a manner which prevents collision with each other.
• One option is to rely on mutual avoidance methodologies between the vehicles. However, such methodologies are prone to congestion when high numbers of vehicles are traversing within limited floor space/paths, consequently leading to failure of the desired tasks being carried out.
• Another option would be to generate collision free paths for each vehicle prior to each vehicle's journey. However, whenever there are high numbers of vehicles traversing within limited floor space/paths, congestion typically results which consequently also leads to failure of the desired tasks being carried out.
• the failure of the aforementioned options is typically due to issues such as, for example: - a dynamic nature of movement for the plurality of vehicles during the course of operations;
• a system for managing a plurality of vehicles including at least one data processor configured to:
• non-conflicting paths are determined using a trajectory of each virtual planning agent, the trajectory including a parameter of a first volume of each virtual planning agent representing a second volume of each corresponding vehicle.
• a data processor implemented method for managing a plurality of vehicles comprising:
• non-conflicting paths are determined using a trajectory of each virtual planning agent, the trajectory including a parameter of a first volume of each virtual planning agent representing a second volume of each corresponding vehicle.
• a server for managing a plurality of vehicles including at least one data processor being configured to:
• a non-transitory computer readable storage medium embodying thereon a program of computer readable instructions which, when executed by one or more processors of a server for managing a plurality of vehicles, in communication with the plurality of vehicles, cause the server to carry out a method for managing a plurality of vehicles, the method embodying the steps of:
• non-conflicting paths are determined using a trajectory of each virtual planning agent, the trajectory including a parameter of a first volume of each virtual planning agent representing a second volume of each corresponding vehicle.
• FIG 1 is a first schematic view of a first system for managing a plurality of vehicles
• FIG 2 is a schematic view of an example server shown in FIG 1 ;
• FIG 3 is a schematic view of an example vehicle shown in FIG 1 ;
• FIG 4 is a schematic view of a second system for managing a plurality of vehicles.
• FIGs 5A to 50 are flow charts of an example for a method for generating navigation routes for a plurality of vehicles.
• Embodiments of the present invention provide users with a system and method for generating navigation routes for a plurality of vehicles.
• the system and method is configured to carry out at least the following aspects for each vehicle, for example:
• the term “vehicle” is interchangeable with the term “robot”, whereby a vehicle is an object that can be controllable and/or programmable to carry out desired tasks.
• the term “agent” is defined to mean a virtual entity representing a vehicle.
• FIG 1. the system 100 includes a plurality of vehicles 120, a communications network 150, and a central server 170. While the central server 170 is shown to be a single processing device, it should be appreciated that the central server 170 can be a plurality of processing devices.
• the plurality of vehicles 120 can be configured to receive data from the central server 170, whereby the data is processed at the plurality of vehicles 120 in order to enable movement of the respective vehicles 120.
• the communications network 150 can be of any appropriate form, such as the Internet and/or a number of local area networks (LANs). It will be appreciated that the configuration shown in FIG 1 is for the purpose of example only, and in practice the vehicles 120, and the central server 170 can communicate via any appropriate mechanism, such as via wired or wireless connections, including, but not limited to mobile networks, private networks, such as an 802.1 1 network, the Internet, LANs, WANs, or the like, as well as via direct or point-to-point connections, such as Bluetooth, or the like. Further details of the respective components of the system 100 will be provided in the following paragraphs.
• Central Server 170
• the central server 170 of any of the examples herein may be formed of any suitable processing device, and one such suitable device is shown in FIG 2.
• the central server 170 is typically administered by, for example, a vehicle fleet management entity or a facility management entity.
• the central server 170 is able to communicate with the plurality of vehicles 120, and/or other processing devices, as required, over the communications network 150 using standard communication protocols.
• the components of the central server 170 can be configured in a variety of ways.
• the components can be implemented entirely by software to be executed on standard computer server hardware, which may comprise one hardware unit or different computer hardware units distributed over various locations, some of which may require the communications network 150 for communication.
• a number of the components or parts thereof may also be implemented by application specific integrated circuits (ASICs) or field programmable gate arrays.
• the central server 170 is a commercially available server computer system based on a 32 bit or a 64 bit Intel architecture, and the processes and/or methods executed or performed by the central server 170 are implemented in the form of programming instructions of one or more software components or modules 202 stored on non-volatile (e.g ., hard disk) computer- readable storage 203 associated with the server 170.
• At least parts of the software modules 202 could alternatively be implemented as one or more dedicated hardware components, such as application-specific integrated circuits (ASICs) and/or field programmable gate arrays (FPGAs).
• ASICs application-specific integrated circuits
• FPGAs field programmable gate arrays
• the server 170 includes at least one or more of the following standard, commercially available, computer components, all interconnected by a bus 205:
• RAM random access memory
• USB universal serial bus
• NIC network interface connector
• a display adapter 208.3 which is connected to a display device 210 such as a liquid-crystal display (LCD) panel device.
• LCD liquid-crystal display
• the server 170 includes a plurality of standard software modules, including:
• OS operating system
• Microsoft Windows Microsoft Windows
• web server software 212 ⁇ e.g., Apache, available at http://www.apache.org);
• scripting language modules 213 ⁇ e.g., personal home page or PHP, available at http://www.php.net, or Microsoft ASP); and
• SQL structured query language
• the web server 212, scripting language 213, and SQL modules 214 provide the server 170 with the general ability to allow devices connected to the network 150 to access the server 170 and in particular to provide data to and receive data from the database 201.
• the boundaries between the modules and components in the software modules 202 are exemplary, and alternative embodiments may merge modules or impose an alternative decomposition of functionality of modules.
• the modules discussed herein may be decomposed into submodules to be executed as multiple computer processes, and, optionally, on multiple computers.
• alternative embodiments may combine multiple instances of a particular module or submodule.
• the operations may be combined or the functionality of the operations may be distributed in additional operations in accordance with the invention.
• Such actions may be embodied in the structure of circuitry that implements such functionality, such as the micro-code of a complex instruction set computer (CISC), firmware programmed into programmable or erasable/programmable devices, the configuration of a field- programmable gate array (FPGA), the design of a gate array or full-custom application-specific integrated circuit (ASIC), or the like.
• CISC complex instruction set computer
• FPGA field- programmable gate array
• ASIC application-specific integrated circuit
• Each of the steps of the processes performed by the server 170 may be executed by a module (of software modules 202) or a portion of a module.
• the processes may be embodied in a non-transient machine-readable and/or computer-readable medium for configuring a computer system to execute the processes.
• the software modules may be stored within and/or transmitted to a computer system memory to configure the computer system to perform the functions of the module.
• the server 170 normally processes information according to a program (a list of internally stored instructions such as a particular application program and/or an operating system) and produces resultant output information via input/output (I/O) devices 208.
• a computer process typically includes an executing (running) program or portion of a program, current program values and state information, and the resources used by the operating system to manage the execution of the process.
• a parent process may spawn other, child processes to help perform the overall functionality of the parent process. Because the parent process specifically spawns the child processes to perform a portion of the overall functionality of the parent process, the functions performed by child processes (and grandchild processes, etc.) may sometimes be described as being performed by the parent process.
• FIG 3. An exemplary embodiment of the vehicle 120 is shown in FIG 3. As shown, the vehicle 120 includes the following components in electronic communication via a bus 306:
• transceiver component 305 that includes N transceivers
• FIG 3 is not intended to be a hardware diagram; thus many of the components depicted in FIG 3 may be realized by common constructs or distributed among additional physical components. Moreover, it is certainly contemplated that other existing and yet-to-be developed physical components and architectures may be utilized to implement the functional components described with reference to FIG 3.
• the vehicle 120 is preferably encased in a robust chassis, and the respective components of the vehicle 120 also are preferably robust so as to be able to withstand regular impacts without being damaged. In some embodiments, the vehicle 120 is configured to carry loads, and can also be configured to dispense the loads carried by the vehicle 120.
• the location sensor 310 can be configured to receive signals from communication nodes to generate location coordinates using, for example, triangulation processes. Alternatively, in outdoor applications, the location sensor 310 can be configured to receive signals from satellites of a Global Positioning System (GPS) and/or Global Navigation Satellite System (GLONASS) network. This allows the vehicle 120 to provide its location in a form of location coordinates whenever necessary.
• GPS Global Positioning System
• GLONASS Global Navigation Satellite System
• the non-volatile memory 303 functions to store (e.g. persistently store) data (including images captured by the image capture component 308) and executable code received by and/or required by the vehicle 120 to carry out desired tasks.
• the non-volatile memory 303 includes bootloader code, modem software, operating system code, file system code, and code to facilitate the implementation of one or more portions of the method as well as other components well known to those of ordinary skill in the art that are not depicted for simplicity.
• the RAM 304 is realized by flash memory (e.g., NAND or NOR memory), but it is certainly contemplated that other memory types may be utilized as well.
• Executable code in the non-volatile memory 303 is typically executed by one or more of the N processing components 301 to effectuate the functional components.
• the image capture component 308 generally operates like a camera to capture images, such as, for example, of objects located around the vehicle 120, whereby the images can be used to determine/confirm a position of the vehicle 120.
• the vehicle controller 307 provides instructions to the vehicle 120 to traverse to a desired location(s) and carry out desired tasks, for example, moving, stopping parking, loading, unloading and so forth. It should be appreciated that the instructions provided by the vehicle controller 307 can be due either to signals received from the central server 170.
• the vehicle controller 307 can also include a set of physical controllers on the vehicle 120.
• the display 302 can be, for example, a LCD or LED panel, which can be used to display a graphical user interface for inputting instructions to the vehicle controller 307, or to display information pertaining to the vehicle 120, for example, faulty codes and status indicators.
• the transceiver component 305 includes N transceiver chains, which may be used for communicating with external devices via wireless networks.
• Each of the N transceiver chains may represent a transceiver associated with a particular communication scheme.
• each transceiver may correspond to protocols that are specific to local area networks, cellular networks (e.g., a CDMA network, a GPRS network, a UMTS networks), and other types of communication networks.
• the system 400 includes a vehicular component 402 continually interacting with an environment 416.
• the vehicular component 402 comprises both a virtual form and a physical form of vehicles or robots. By interacting with the environment 416, the vehicular component 402 is able to make appropriate decisions for each individual vehicle or robot.
• the vehicular component 402 includes a multi-agent system 404, and a robotic fleet 410.
• individual vehicles of the robotic fleet 410 are each represented virtually in the multi-agent system 404.
• the multi-agent system 404 is typically able to simulate movements of the robotic fleet 410 to ensure that desired tasks of the robotic fleet 410 can be carried out.
• the environment 416 typically encompasses aspects such as, for example, layout of a facility, configuration of production line, human movements at the facility, machinery placements at the facility, computing resource placements at the facility, sensor placements at the facility, and so forth.
• the environment 416 typically provides inputs/percepts 412 (obtained using sensors) to the multi-agent system 404, whereby the inputs/percepts 412 includes, for example, pending tasks, path obstructions, route modifications and the like.
• the robotic fleet 410 also provides inputs/percepts 406 (obtained using sensors) to the multi-agent system 404, whereby the inputs/percepts 406 includes, for example, respective positions, respective states, respective actions, and so forth.
• the multi-agent system 404 After processing the inputs/percepts 406, 412, the multi-agent system 404 transmits decisions 408 to the robotic fleet 410, the robotic fleet 410 being instructed to act on the decisions 408, which includes navigation routes for the respective fleet units.
• the robotic fleet 410 when the robotic fleet carries out the decisions 408, the robotic fleet 410 then provides outputs/actions 414 to the environment 416, the outputs/actions 414 including information on respective payloads, resolutions of path conflicts, obstacle avoidance routes and so forth. Subsequently, both the environment 416 and the robotic fleet 410 continually feed back the inputs/percepts 412, 406 to the multi-agent system 404, enabling appropriate decisions to be made by the vehicular component 402 in real-time.
• system 400 is able to provide a robotic fleet which is able to allow respective fleet units to traverse, load payloads, wait and unload payloads in a desired manner within a facility without undesired incidents.
• a first example of a method 500 for managing a plurality of vehicles will now be described with reference to FIG 5.
• the method 500 generally relies on, for example, the central server 170 for carrying out an assessment of the plurality of vehicles before transmitting appropriate outcomes to the plurality of vehicles. While the method 500 is described with respect to the system 400, it should be noted that the method 500 need not be carried out in an identical system 400. For example, the method 500 can be carried out in a decentralised manner, whereby multiple servers and even the processor 301 on each respective vehicle 120 are used to enable the carrying out of the method 500.
• the inputs/percepts 406, 412 are processed at the multi-agent system 404 to acquire real-time data from the environment 416 and the robotic fleet 410.
• a stateful initialisation of virtual planning agents is performed at the multi-agent system 404.
• actions to be taken by the virtual planning agents in a current iteration are generated at step 530. Consequently, the multi-agent system 404 runs a multi-agent simulation at step 540.
• step 550 It is determined at step 550 if all agents' path are non-conflicting in relation to both space and time parameters. If true, planned routes are transmitted to the individual vehicles of the robotic fleet 410 at step 570. This is indicated as the decisions 408. If false, dynamic course correction is performed for agents with conflicting paths at step 560, and subsequently, step 550 is carried out again.
• FIG 5A shows a generalisation of many of the steps of the method 500. Subsequent FIGs 5B to 50 will depict more detailed break-downs of respective steps of the method 500.
• the multi-agent system 404 regenerates past system states.
• the system 404 is configured to run in real-time and to react in a dynamic environment, the system 404 typically runs continuously.
• the decisions (408) made in the past affects decisions made in the present.
• the regeneration of past system states involves interpreting what the system 404 has done in the past and combining it with current information about the current environment. For example if an agent has already found a path to its goal a minute ago and is already heading towards its destination, it should continue on its path unless there are obstructions along the agent’s path.
• the system 404 collects information from the environment and combines it together with the current agent’s path to determine if rerouting is necessary (for example, if there are any obstructions along the current path).
• the multi-agent system 404 carries out a prediction of potential outcomes based on prior system states at step 522, and then proceeds to step 530.
• this step is related to step 518.
• the prediction outcomes can include, for example, re-routing agents in order to avoid collisions, continuing normal operation as earlier planned if no new situations have been determined and so forth.
• Step 540 there is shown a break-down of the step 530.
• the multi-agent system 404 enumerates potential decision policies based on predicted outcomes and previous system states, and subsequently, at step 532, the planning agents are populated with system states, potential outcomes and decision policies. Step 540 then follows.
• Step 538 it is determined at the multi-agent system 404 if all agents have completed the planning process. If true, all decision outcomes are consolidated at step 544. Step 570 subsequently follows.
• the multi-agent system 404 selects an agent with a highest priority at step 542, and subsequently attempts to find a feasible path to a goal at step 546.
• step 562 it is determined at the multi-agent system 404 if there are any alternative destinations en route to the goal. If false, the planning agent remains at the current location at step 564, and proceeds to step 550.
• the multi-agent system 404 attempts to locate a feasible path to the new goal at step 566, and at step 568, it is determined if the feasible path can be found. If true, step 550 follows. If false, step 562 follows.
• a route tracker, tracker and clock of the multi-agent system 404 is initialised. In addition, unexplored regions are also mapped.
• step 930 a next point in unexplored regions is selected at step 925. If unexplored regions are available, step 930 follows. If there are no unexplored regions, step 920 follows. Subsequently, it is determined at step 930 if the current point of the agent is at the goal for the agent. If true, it is determined at step 940 if the agent is able to remain at the goal until t max , being a maximum simulation time that the agent should be able to remain at the goal before the simulation terminates. If true, a trajectory for the agent is plotted at step 945, before proceeding to step 920. If false, step 920 follows. It should be noted that trajectory refers to a path in space- time. If false for step 930, the multi-agent system 404 gets all adjacent points to the current point at step 935, and proceeds to step 950 to get subsequent adjacent points to the current point.
• timings for the respective agents are generated at step 955, and it is determined at step 960 if a route to an adjacent point is available in space-time. If true, the point is added to the route tracker at step 965, and step 950 follows. If false for step 960, it is determined at step 970 if exploratory time window f has been exceeded. If true, step 950 follows. If false, it is determined at step 975 if current point is available after waiting for G, a pre-determined waiting time. If true for step 975, step 960 follows. If false for step 975, step 950 follows.
• the exploratory time window f is a maximum duration that the agent can remain stationary at its current location while determining subsequent movement for the agent.
• step 915 there is shown a break-down of step 915. From step 910, it is determined at step 1010 if the agent is at the goal. If true, step 920 follows. If false, it is determined at step 1015 if the agent's goal is occupied. If true, step 920 follows. If false for step 1015, it is determined at step 1020 if there is a path from agent's start point to the goal. If false for step 1020, step 920 follows. If true for step 1020, step 925 follows. Referring to FIG 5H, there is shown a break-down of step 925. From step 915, step 1025 appends a start point of an agent to unexplored regions.
• step 1030 it is determined at step 1030 if there are unexplored regions. Step 950 can also lead to step 1030. If false for step 1030, step 920 follows. If true for step 1030, step 1035 follows by removal of point with highest priority from unexplored regions, and step 1040 follows with the set point being defined as the current point. Step 930 then follows.
• FIG 51 follows with a break-down of step 935.
• Step 1045 follows step 930.
• the current time is updated to a time when the agent arrives at the current point.
• step 1050 all adjacent points are gotten for the current point.
• Step 950 then follows.
• step 1055 determines if there are more adjacent points. If false, step 925 follows. If true, step 1060 computes a cumulative cost for the agent to reach respective adjacent points. At step 1065, the adjacent point with lowest cost is selected. At step 1070, it is determined if traversal to the adjacent point creates a circular loop. If false, step 955 follows. If true, step 1075 follows. Steps 965, 970 and 975 can also lead to step 1075. At step 1075, it is determined if there are more adjacent points. If false for step 1075, step 925 follows. If true for step 1075, an adjacent point is removed from consideration at step 1080, and step 1065 follows.
• step 1085 From step 950, step 1085 generates timings such as, for example, arrival times, travel times, stationary times, and so forth. Subsequently, step 1090 follows, which adds routes from a current point to an adjacent point for the route tracker. Step 960 then follows.
• step 1095 determines if a route to the adjacent point is available. If false, step 970 follows. If true, step 1100 determines if the agent can remain for Q (a pre defined time) at an adjacent point after arrival at the adjacent point. If false for step 1 100, step 970 follows. If true for step 1 100, step 965 follows.
• step 965 a break-down of step 965 is shown.
• step 1 105 it is determined if the adjacent point is in the route tracker. If false, step 950 follows. If true, at step 1 1 10, it is determined if the cost to the adjacent point is less than the cost to the current point. If false for step 1 1 10, step 950 follows. If true for step 1 1 10, step 1 115 follows, and an adjacent point is added to the route tracker. Subsequently, priority is generated for the adjacent point at step 1 120, and step 1 125 follows, which adds priority and an adjacent point to unexplored regions. Step 950 then follows.
• step 960 proceeds to step 1 130, which advances exploratory time by G starting from the current time. Subsequently, step 1 135 determines if the exploratory time is greater than current time + cp. If false, step 975 follows. If true, step 950 follows.
• Step 970 proceeds to step 1 140, which updates timings, for example, arrival time, stationary time, current time, and so forth. Subsequently, step 1 145 determines if an agent can remain at a current point for the exploratory time. If false, step 950 follows, and if true, step 960 follows.
• a trajectory (a path in space-time) is checked to determine if there is any intersection with the trajectories of other agents.
• the trajectory can be perceived to be a volume that the agent occupies and how it changes over time.
• the volume of an agent can change in both the space and time dimension as it traverses a route, it can also change in the time dimension alone as the agent remains stationary, it can also scale in size or change in the space dimension alone as a forecast is made of the agent’s size to prevent other agents from crossing its path as it performs activities at a desired destination such as picking objects and so forth.
• Such computations require a determination of the size and kinematics e.g. speed, area and volume of the actual robot.
• the system and method as described in the preceding paragraphs are configured to enable: a. Planning and assigning coordinated routes such that vehicles/robots share the limited area allocated for vehicles/robots in space and time to efficiently manage space available. This will result in, for example, vehicles/robots moving in the same direction following each other by shared reservation rather than exclusive reservation, vehicles/robots moving in opposing directions use routes in the time allocated, such that obstruction-free bidirectional traffic is possible without needing to stop/park outside the travel route in order to give way, and so forth; b. Resilience to poor network conditions by incorporating newly available information into the planning iteration and performing replanning to ensure all vehicles/robots reach their respective destinations on time while avoiding collisions;

Landscapes

• Engineering & Computer Science (AREA)
• Radar, Positioning & Navigation (AREA)
• Remote Sensing (AREA)
• Automation & Control Theory (AREA)
• Physics & Mathematics (AREA)
• General Physics & Mathematics (AREA)
• Aviation & Aerospace Engineering (AREA)
• Traffic Control Systems (AREA)
• Navigation (AREA)

Applications Claiming Priority (1)

Publications (2)

Family

ID=68467045

Family Applications (1)

Country Status (4)

Families Citing this family (4)

Family Cites Families (4)

• 2018
  • 2018-05-11 EP EP18918111.8A patent/EP3791134A4/de not_active Withdrawn
  • 2018-05-11 WO PCT/SG2018/050231 patent/WO2019216822A1/en active Application Filing
  • 2018-05-11 SG SG11202011026PA patent/SG11202011026PA/en unknown
• 2019
  • 2019-05-09 TW TW108116103A patent/TWI702377B/zh not_active IP Right Cessation

Also Published As

Similar Documents

Legal Events