Physics-Aware Safety-Assured Design of Hierarchical Neural Network based Planner

Huang, Chao; Wang, Yixuan; Bowen, Zheng,; Zhu, Qi

doi:10.1109/iccps54341.2022.00019

Cited by 15 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work in [3] proposes a hierarchical reinforcement and imitation learning (H-REIL) approach specifically for near-accident scenarios, which consists of low-level policies learned by imitation learning (IL) for discrete driving modes, and a high-level policy learned by reinforcement learning (RL) that switches between different driving modes. [18] proves the strength of a hierarchical neural network based planner regarding safety and verifiability, compared with a single neural network based planner.…”

Section: Related Workmentioning

confidence: 77%

Connectivity Enhanced Safe Neural Network Planner for Lane Changing in Mixed Traffic

Jiao¹,

Zheng²,

Liang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Connectivity technology has shown great potentials in improving the safety and efficiency of transportation systems by providing information beyond the perception and prediction capabilities of individual vehicles. However, it is expected that human-driven and autonomous vehicles, and connected and non-connected vehicles need to share the transportation network during the transition period to fully connected and automated transportation systems. Such mixed traffic scenarios significantly increase the complexity in analyzing system behavior and quantifying uncertainty for highly interactive scenarios, e.g., lane changing. It is even harder to ensure system safety when neural network based planners are leveraged to further improve efficiency. In this work, we propose a connectivity-enhanced neural network based lane changing planner. By cooperating with surrounding connected vehicles in dynamic environment, our proposed planner will adapt its planned trajectory according to the analysis of a safe evasion trajectory. We demonstrate the strength of our planner design in improving efficiency and ensuring safety in various mixed traffic scenarios with extensive simulations. We also analyze the system robustness when the communication or coordination is not perfect.

show abstract

Section: Related Workmentioning

confidence: 77%

Connectivity Enhanced Safe Neural Network Planner for Lane Changing in Mixed Traffic

Jiao¹,

Zheng²,

Liang³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…However, the existing safety verification methods are subject to limited efficiency and accuracy for safety-critical systems that are time-sensitive and operate in dynamic environments [20]. Further, computing the exact reachable set for most nonlinear systems is a complex problem [14], and deployment of LEC aggravates the complexity of the problem.…”

Section: Myopic Action Selectormentioning

confidence: 99%

Dynamic Simplex: Balancing Safety and Performance in Autonomous Cyber Physical Systems

Luo¹,

Ramakrishna²,

Pettet³

et al. 2023

Preprint

View full text Add to dashboard Cite

Learning Enabled Components (LEC) have greatly assisted cyberphysical systems in achieving higher levels of autonomy. However, LEC's susceptibility to dynamic and uncertain operating conditions is a critical challenge for the safety of these systems. Redundant controller architectures have been widely adopted for safety assurance in such contexts. These architectures augment LEC "performant" controllers that are difficult to verify with "safety" controllers and the decision logic to switch between them. While these architectures ensure safety, we point out two limitations. First, they are trained offline to learn a conservative policy of always selecting a controller that maintains the system's safety, which limits the system's adaptability to dynamic and non-stationary environments. Second, they do not support reverse switching from the safety controller to the performant controller, even when the threat to safety is no longer present. To address these limitations, we propose a dynamic simplex strategy with an online controller switching logic that allows two-way switching. We consider switching as a sequential decision-making problem and model it as a semi-Markov decision process. We leverage a combination of a myopic selector using surrogate models (for the forward switch) and a non-myopic planner (for the reverse switch) to balance safety and performance. We evaluate this approach using an autonomous vehicle case study in the CARLA simulator using different driving conditions, locations, and component failures. We show that the proposed approach results in fewer collisions and higher performance than state-ofthe-art alternatives.

show abstract

“…[38] acquires a strategic level k planner for merging in dense traffic by reinforcement learning and iterative reasoning. But these learning-based methods are hard and expensive to assure safety [39], [40], [41], [42], [43], [44].…”

Section: B Interaction In Dense Trafficmentioning

confidence: 99%

Interactive Trajectory Planner for Mandatory Lane Changing in Dense Non-Cooperative Traffic

Chen¹,

Li²,

Zhang³

et al. 2023

Preprint

View full text Add to dashboard Cite

When the traffic stream is extremely congested and surrounding vehicles are not cooperative, the mandatory lane changing can be significantly difficult. In this work, we propose an interactive trajectory planner, which will firstly attempt to change lanes as long as safety is ensured. Based on receding horizon planning, the ego vehicle can abort or continue changing lanes according to surrounding vehicles' reactions. We demonstrate the performance of our planner in extensive simulations with eight surrounding vehicles, initial velocity ranging from 0.5 to 5 meters per second, and bumper to bumper gap ranging from 4 to 10 meters. The ego vehicle with our planner can change lanes safely and smoothly. The computation time of the planner at every step is within 10 milliseconds in most cases on a laptop with 1.8GHz Intel Core i7-10610U.

show abstract

Physics-Aware Safety-Assured Design of Hierarchical Neural Network based Planner

Cited by 15 publications

References 25 publications

Connectivity Enhanced Safe Neural Network Planner for Lane Changing in Mixed Traffic

Connectivity Enhanced Safe Neural Network Planner for Lane Changing in Mixed Traffic

Dynamic Simplex: Balancing Safety and Performance in Autonomous Cyber Physical Systems

Interactive Trajectory Planner for Mandatory Lane Changing in Dense Non-Cooperative Traffic

Contact Info

Product

Resources

About