Toward Trustworthy Decision-Making for Autonomous Vehicles:A Robust Reinforcement Learning Approach with Safety Guarantees

While autonomous vehicles are vital components of intelligent transportation systems,ensuring the trustworthiness of decision-making remains a substantial challenge in realizing autonomous driving.Therefore,we present a novel robust reinforcement learning approach with safety guarantees to attain trustworthy decision-making for autonomous vehicles.The proposed technique ensures decision trustworthiness in terms of policy robustness and collision safety.Specifically,an adversary model is learned online to simulate the worst-case uncertainty by approximating the optimal adversarial perturbations on the observed states and environmental dynamics.In addition,an adversarial robust actor-critic algorithm is developed to enable the agent to learn robust policies against perturbations in observations and dynamics.Moreover,we devise a safety mask to guarantee the collision safety of the autonomous driving agent during both the training and testing processes using an interpretable knowledge model known as the Responsibility-Sensitive Safety Model.Finally,the proposed approach is evaluated through both simulations and experiments.These results indicate that the autonomous driving agent can make trustworthy decisions and drastically reduce the number of collisions through robust safety policies.

Towards Energy-Efficient Autonomous Driving: A Multi-Objective Reinforcement Learning Approach

Dear Editor, With the development of automobile industry and artificial intelligence(AI) domains, autonomous vehicles(AVs) are becoming a reality and promise to revolutionize human mobility [1]–[3]. The decision-making system of AVs is crucial, which is typically required to trade off multiple competing objectives. For example,when determining driving policies.

Towards Safe Autonomous Driving:Decision Making with Observation‑Robust Reinforcement Learning

Most real-world situations involve unavoidable measurement noises or perception errors which result in unsafe decision making or even casualty in autonomous driving.To address these issues and further improve safety,automated driving is required to be capable of handling perception uncertainties.Here,this paper presents an observation-robust reinforcement learning against observational uncertainties to realize safe decision making for autonomous vehicles.Specifically,an adversarial agent is trained online to generate optimal adversarial attacks on observations,which attempts to amplify the average variation distance on perturbed policies.In addition,an observation-robust actor-critic approach is developed to enable the agent to learn the optimal policies and ensure that the changes of the policies perturbed by optimal adversarial attacks remain within a certain bound.Lastly,the safe decision making scheme is evaluated on a lane change task under complex highway traffic scenarios.The results show that the developed approach can ensure autonomous driving performance,as well as the policy robustness against adversarial attacks on observations.

Polar codes: Encoding/decoding and rate-compatible jointly design for HARQ system

Polar coding are the first class of provable capacity-achieving coding techniques for a wide range of channels.With an ideal recursive structure and many elegant mathematical properties,polar codes are inherently implemented with low complexity encoding and decoding algorithms.Since the block length of the original polar construction is limited to powers of two,rate-compatible polar codes(RCPC)are presented to meet the flexible length/rate transmission requirements in practice.The RCPC codes are well-conditioned to combine with the hybrid automatic repeat request(HARQ)system,providing high throughput efficiency and such RCPC-HAPQ scheme is commonly used in delay-insensitive communication system.This paper first gives a survey of both the classical and state-of-the-art encoding/decoding algorithms for polar codes.Then the RCPC construction methods are discussed,including the puncturing,shortening,multi-kernel construction,etc.Finally,we investigate several RCPC-HARQ jointly design systems and discuss their encoding gain and re-transmission diversity gain.