Adversarial Agent Behavior Learning in Autonomous Driving Using Deep Reinforcement Learning
By: Arjun Srinivasan, Anubhav Paras, Aniket Bera
Potential Business Impact:
Teaches self-driving cars to avoid bad drivers.
Existing approaches in reinforcement learning train an agent to learn desired optimal behavior in an environment with rule based surrounding agents. In safety critical applications such as autonomous driving it is crucial that the rule based agents are modelled properly. Several behavior modelling strategies and IDM models are used currently to model the surrounding agents. We present a learning based method to derive the adversarial behavior for the rule based agents to cause failure scenarios. We evaluate our adversarial agent against all the rule based agents and show the decrease in cumulative reward.
Similar Papers
Robust Driving Control for Autonomous Vehicles: An Intelligent General-sum Constrained Adversarial Reinforcement Learning Approach
Machine Learning (CS)
Makes self-driving cars safer from tricky computer attacks.
Diverse and Adaptive Behavior Curriculum for Autonomous Driving: A Student-Teacher Framework with Multi-Agent RL
Robotics
Teaches cars to drive safely in all traffic.
Attacking Autonomous Driving Agents with Adversarial Machine Learning: A Holistic Evaluation with the CARLA Leaderboard
Cryptography and Security
Makes self-driving cars safer from fake signs.