IEEE Transactions on Intelligent Transportation Systems · 2022 · 91 citations · 26 references
ComputingAutonomous SystemsRobotics EngineeringAutonomous VehiclesMachine LearningMotion PlanningRapidly Exploring Random TreesReinforcement LearningRobot Motion PlanningTrajectory AnalysisTrajectory GenerationAction SequenceAutonomous Vehicle Path PlanningComputational EfficiencyComputational Efficiency AnalysisFeasible Motion PlanningGenerative Adversarial NetworksTrajectory Planning
Trajectory planning is essential for self-driving vehicles and has stringent requirements for accuracy and efficiency. The existing trajectory planning methods have limitations in the feasibility of planned trajectories and computational efficiency. This paper proposes a life-long learning framework to achieve effective and high-accuracy direct trajectory planning (DTP) tasks. Based on generative adversarial networks (GANs), this study develops a lightweight GDTP model to map the initial/final states and the control action sequence. Additionally, by embedding the GDTP into the rapidly-exploring random tree (RRT), a GDTP-RRT algorithm is further designed for long-distance and multi-stage planning tasks. Taking the tractor-trailer as an application case, we test the proposed method in multiple scenarios with varying characteristics. The experimental results show that the method can plan highly feasible trajectories in a short time, compared with the most applied algorithm – the cubic curve RRT* (CCRRT*). It is found that the tracking errors of our method are 29.1% and 44.1% lower than the CCRRT* in terms of position and heading angle. This paper provides an effective and stable vehicle trajectory planning method for complex self-driving tasks.
26
Generative adversarial networks
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza et al. · Communications of the ACM · 2020 · 13.6K citations · Full text
Rapidly-exploring random trees : a new tool for path planning
Steven M. LaValle · 1998 · 3.6K citations
Stanley: The robot that won the DARPA Grand Challenge
Sebastian Thrun, Mike Montemerlo, Hendrik Dahlkamp et al. · Journal of Field Robotics · 2006 · 2.1K citations · Full text