Navigating Occluded Intersections with Autonomous Vehicles Using Deep Reinforcement Learning

By David Isele, Reza Rahimi, Akansel Cosgun, Kaushik Subramanian, Kikuo Fujimura. 2018

277 citations recorded by the source corpus.

Providing an efficient strategy to navigate safely through unsignaled intersections is a difficult task that requires determining the intent of other drivers. We explore the effectiveness of Deep Reinforcement Learning to handle intersection problems. Using recent advances in Deep RL, we are 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. We then explore a system's ability to learn active sensing behaviors to enable navigating safely in the case of occlusions. Our analysis, provides insight into the intersection handling problem, the solutions learned by the network point out several shortcomings of current rule-based methods, and the failures of our current deep reinforcement learning system point to future research directions.

Subfields: Automotive Engineering, Control and Systems Engineering, Safety, Risk, Reliability and Quality

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Control and Systems Engineering

In Safety, Risk, Reliability and Quality

Praveen Palanisamy

Citations in the corpus

Deep Reinforcement Learning for Autonomous Driving: A Survey (2020, methodology): “Path planning in dynamic environments and varying vehicle dynamics is a key problem in autonomous driving, for example negotiating right to pass through in an intersection [86], merging into highways.”
Reward (Mis)design for Autonomous Driving (2021, methodology): “Calculations of safety indifference points are given below for the two papers for which τcrash ≺ τidle ≺ τsucc [8,23].”
Distributed Multiagent Coordinated Learning for Autonomous Driving in Highways Based on Dynamic Coordination Graphs (2020, background): “braking system control [12], ramp-metering [13], autonomous intersection management [14], and lane keeping/changing”
Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey (2020, methodology): “[128] DQN Autonomous driving Navigating in occluded intersections SUMO TTC [129]”
CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning (2018, background): “SUMO: Previous work modeled autonomous driving tasks as MDPs in which all other vehicles do not learn to respond to a single learning agent (Isele et al., 2018; Kuefler et al., 2017).”
Multi-Agent Connected Autonomous Driving using Deep Reinforcement Learning (2019, methodology): “Learning algorithms can be used to solve the tasks in an integrated/end-to-end fashion [13] [14] or in an isolated approach for each driving task like intersectiondriving [15] [16] and lane-changing [17].”
Deep Reinforcement Learning for Cyber Security (2019, background): “Atari [28], [29], game of Go [30], [31], realtime strategy game StarCraft II [32]–[35], 3D multi-player game Quake III Arena Capture the Flag [36], and teamwork game Dota 2 [37] to real-world applications such as robotics [38], autonomous vehicles [39], autonomous surgery [40],”