Sampling-Based Optimal Trajectory Generation for Autonomous Vehicles Using Reachable Sets

Würsching, Gerald; Althoff, Matthias

doi:10.1109/itsc48978.2021.9564801

Cited by 20 publications

(12 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After predicting traffic-rule-compliant future occupancies of other traffic participants, we need to determine the collisionfree solution space to project the actions of the RL agent onto a safe area (14). It has been shown that using the reachable set of the ego vehicle to obtain constraints for an optimization-based motion planner [66] as well as to adjust the sampling intervals for a sampling-based motion planner [67] can effectively reduce computation time for complex traffic scenarios.…”

Section: B Computation Of Reachable Sets For the Ego Vehiclementioning

confidence: 99%

Safe Reinforcement Learning for Automated Vehicles via Online Reachability Analysis

Wang,

Althoff

2024

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

Ensuring safe and capable motion planning is paramount for automated vehicles. Traditional methods are limited in their ability to handle complex and unpredictable traffic situations. Model-free reinforcement learning (RL) addresses this challenge by generalizing across different traffic situations without requiring explicit knowledge of all possible outcomes. However, it also poses challenges due to its inherent lack of safety guarantees. To bridge this gap, we integrate online reachability analysis into model-free RL to provide realtime safety guarantees. Reachability analysis helps to identify unsafe states and actions, enabling provably safe decision-making in automated vehicles. We evaluate the effectiveness of our approach through extensive numerical experiments. Our results demonstrate that we can efficiently provide safety guarantees without impairing the performance of the learned agent.

show abstract

Section: B Computation Of Reachable Sets For the Ego Vehiclementioning

confidence: 99%

Safe Reinforcement Learning for Automated Vehicles via Online Reachability Analysis

Wang,

Althoff

2024

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

show abstract

“…They also combined driving corridors with a sampling-based motion planner that uses reachability analysis to determine collision-free drivable areas for the subject vehicle. It can continuously adjust its sampling interval according to the rapidly changing environment in the traffic scene, thereby significantly reducing the number of samples and computation time required for planning [18]. A study by the Hong Kong University of Science and Technology proposed a method for the online trajectory generation of quadrotor aircraft in unknown environments.…”

Section: Related Workmentioning

confidence: 99%

“…However, trajectory generation for configuration spaces with high degrees of freedom is inefficient and easily falls into local minima; therefore, this method is generally suitable for low-dimensional configuration spaces. Discretization methods [18], [25]- [29], such as state lattices, typically cannot meet the demand when driving situations suddenly become more hazardous. In addition, considering the execution efficiency of the computer, the granularity of discretization cannot be too high; otherwise, it may not be possible to discover narrow passages quickly enough to generate feasible motions in a critical situation.…”

Section: Related Workmentioning

confidence: 99%

Motion Planning for Dynamic Scenario Vehicles in Autonomous-Driving Simulations

2023

IEEE Access

View full text Add to dashboard Cite

Scenario vehicles are an important part of the dynamic environment utilized in autonomousdriving simulations. They are required to meet the demands of traffic-scenario diversity and form a larger coverage scale in the road network. However, the current motion planning of scenario vehicles either adheres to the classical microscopic traffic-flow model or follows a predefined path; thus, interacting with the vehicle under test in a dynamic bidirectional fashion is difficult. This study researches a motion-planning method for a broader category of unmanned vehicles and proposes a motion-planning method for scenario vehicles based on Pontryagin's minimal principle, used in optimal control theory and the closed-form solution of the minimum snap method. The study reclassifies actions received from the behavior layer according to the boundary conditions and final times and derives an analytical solution for each of them. The analytical solution is then experimentally verified. The proposed method not only accomplishes efficient motion planning but also exhibits variant driving styles, which provides a practical solution for the motion planning of scenario vehicles in simulations.

show abstract

“…A graph-based algorithm for finding these trajectories can be found in [105]. A reachable set-based solution on the given problem is proposed by [106]. Moreover, it is necessary to select one trajectory from the set of feasible trajectories, in which selection process energy, comfort or time performance requirements can be involved [100].…”

Section: Formulation and Solution Of The Control Problemmentioning

confidence: 99%

Coordinated Control Design for Ethical Maneuvering of Autonomous Vehicles

Németh

2023

Energies

View full text Add to dashboard Cite

This paper proposes a coordinated control design method, with which the autonomous vehicle is able to perform ethical maneuvers. The starting point of the provided method is a thorough analysis on the ethical concepts for autonomous vehicle control design methods. Using the results of the analysis, an own concept is provided based on some principles of Protestant ethics. The concept focuses on improving trust in vehicle control through clear rules and predictable vehicle motion, and it is in line with the state-of-the-art ethical vehicle control methods. Moreover, an optimal Model Predictive Control (MPC) design method is formed, in which the provided ethical concept is incorporated. The outputs of the optimal control are steering angle and velocity profile, with which the ethical maneuvering can be achieved. The contribution of the paper is a coordinated control design method, which is able to involve ethical principles. Moreover, the application of Protestant ethics in this context is also a novel achievement in the paper. The effectiveness of the method through different simulation scenarios is illustrated.

show abstract

Sampling-Based Optimal Trajectory Generation for Autonomous Vehicles Using Reachable Sets

Cited by 20 publications

References 31 publications

Safe Reinforcement Learning for Automated Vehicles via Online Reachability Analysis

Safe Reinforcement Learning for Automated Vehicles via Online Reachability Analysis

Motion Planning for Dynamic Scenario Vehicles in Autonomous-Driving Simulations

Coordinated Control Design for Ethical Maneuvering of Autonomous Vehicles

Contact Info

Product

Resources

About