Corpus ID: 235899151

Minimizing Safety Interference for Safe and Comfortable Automated Driving with Distributional Reinforcement Learning

  title={Minimizing Safety Interference for Safe and Comfortable Automated Driving with Distributional Reinforcement Learning},
  author={Danial Kamran and Tizian Engelgeh and Marvin Busch and Johannes Fischer and Christoph Stiller},
Despite recent advances in reinforcement learning (RL), its application in safety critical domains like autonomous vehicles is still challenging. Although punishing RL agents for risky situations can help to learn safe policies, it may also lead to highly conservative behavior. In this paper, we propose a distributional RL framework in order to learn adaptive policies that can tune their level of conservativity at run-time based on the desired comfort and utility. Using a proactive safety… Expand

Figures and Tables from this paper


Worst Cases Policy Gradients
This work proposes an actor-critic framework that models the uncertainty of the future and simultaneously learns a policy based on that uncertainty model, and optimize policies for varying levels of conditional Value-at-Risk. Expand
High-level Decision Making for Safe and Reasonable Autonomous Lane Changing using Reinforcement Learning
A deep reinforcement learning (RL) agent is let to drive as close as possible to a desired velocity by executing reasonable lane changes on simulated highways with an arbitrary number of lanes by making use of a minimal state representation and a Deep Q-Network. Expand
Risk-Aware High-level Decisions for Automated Driving at Occluded Intersections with Reinforcement Learning
A generic risk-aware DQN approach in order to learn high level actions for driving through unsignalized occluded intersections and proposes a risk based reward function which punishes risky situations instead of only collision failures. Expand
Safe Reinforcement Learning via Shielding
A new approach to learn optimal policies while enforcing properties expressed in temporal logic by synthesizing a reactive system called a shield, which monitors the actions from the learner and corrects them only if the chosen action causes a violation of the specification. Expand
Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving
This paper applies deep reinforcement learning to the problem of forming long term driving strategies and shows how policy gradient iterations can be used without Markovian assumptions, and decomposes the problem into a composition of a Policy for Desires and trajectory planning with hard constraints. Expand
Safe Reinforcement Learning on Autonomous Vehicles
This work investigates how prediction provides a general and intuitive framework to constraint exploration, and shows how it can be used to safely learn intersection handling behaviors on an autonomous vehicle. Expand
Runtime Safety Assurance Using Reinforcement Learning
A learned meta-controller capable of identifying unsafe situations with high accuracy is designed, frame the design of RTSA with the Markov decision process (MDP) framework and use reinforcement learning (RL) to solve the problem. Expand
Navigating Occluded Intersections with Autonomous Vehicles Using Deep Reinforcement Learning
Using recent advances in Deep RL, a system is able to learn policies that surpass the performance of a commonly-used heuristic approach in several metrics including task completion time and goal success rate and have limited ability to generalize. Expand
Safe Reinforcement Learning with Scene Decomposition for Navigating Complex Urban Environments
This work proposes a modular decision making algorithm to autonomously navigate intersections, addressing challenges of existing rule-based and reinforcement learning (RL) approaches, and introduces a belief update technique using a learning based approach. Expand
Distributional Reinforcement Learning with Quantile Regression
A distributional approach to reinforcement learning in which the distribution over returns is modeled explicitly instead of only estimating the mean is built, and a novel distributional reinforcement learning algorithm is presented consistent with the theoretical formulation. Expand