Deep Reinforcement Learning for Human-Like Driving Policies in Collision Avoidance Tasks of Self-Driving Cars

2020-06-07 · Ran Emuna, Avinoam Borowsky, Armin Biess

The technological and scientific challenges involved in the development of autonomous vehicles (AVs) are currently of primary interest for many automobile companies and research labs. However, human-controlled vehicles are likely to remain on the roads for several decades to come and may share with AVs the traffic environments of the future. In such mixed environments, AVs should deploy human-like driving policies and negotiation skills to enable smooth traffic flow. To generate automated human-like driving policies, we introduce a model-free, deep reinforcement learning approach to imitate an experienced human driver's behavior. We study a static obstacle avoidance task on a two-lane highway road in simulation (Unity). Our control algorithm receives a stochastic feedback signal from two sources: a model-driven part, encoding simple driving rules, such as lane-keeping and speed control, and a stochastic, data-driven part, incorporating human expert knowledge from driving data. To assess the similarity between machine and human driving, we model distributions of track position and speed as Gaussian processes. We demonstrate that our approach leads to human-like driving policies.

📄 PDF Abstract BibTeX arXiv:2006.04218

Code (1)

emunaran/stochastic-human-driving-policies-drl 공식 구현 pytorch

Tasks

Autonomous Vehicles Collision AvoidanceDeep Reinforcement LearningGaussian ProcessesSelf-Driving CarsUnity

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios

2022-12-21 · Yiren Lu, Justin Fu, George Tucker, Xinlei Pan 외

Imitation learning (IL) is a simple and powerful way to use high-quality human driving data, which can be collected at scale, to produce human-like behavior. However, policies based on imitation learning alone often fail…

Autonomous Driving Imitation Learning reinforcement-learning Reinforcement Learning+1

HAD-Gen: Human-like and Diverse Driving Behavior Modeling for Controllable Scenario Generation

2025-03-19 · Cheng Wang, Lingxin Kong, Massimiliano Tamborski, Stefano V. Albrecht

Simulation-based testing has emerged as an essential tool for verifying and validating autonomous vehicles (AVs). However, contemporary methodologies, such as deterministic and imitation learning-based driver models, str…

Autonomous Vehicles Imitation Learning Multi-agent Reinforcement Learning reinforcement-learning+1

Multi-Vehicle Mixed-Reality Reinforcement Learning for Autonomous Multi-Lane Driving

2019-11-26 · Rupert Mitchell, Jenny Fletcher, Jacopo Panerati, Amanda Prorok

Autonomous driving promises to transform road transport. Multi-vehicle and multi-lane scenarios, however, present unique challenges due to constrained navigation and unpredictable vehicle interactions. Learning-based met…

Autonomous Driving Autonomous Vehicles Deep Reinforcement Learning Mixed Reality+3

Autonomous Vehicle Collision Avoidance With Racing Parameterized Deep Reinforcement Learning

2026-04-17 · Shathushan Sivashangaran, Vihaan Dutta, Apoorva Khairnar, Sepideh Gohari 외 arxiv

Road traffic accidents are a leading cause of fatalities worldwide. In the US, human error causes 94% of crashes, resulting in excess of 7,000 pedestrian fatalities and $500 billion in costs annually. Autonomous Vehicles…

Computational Efficiency Reinforcement Learning Autonomous Vehicles Collision Avoidance

Planning on the fast lane: Learning to interact using attention mechanisms in path integral inverse reinforcement learning

2020-07-11 · Sascha Rosbach, Xing Li, Simon Großjohann, Silviu Homoceanu 외

General-purpose trajectory planning algorithms for automated driving utilize complex reward functions to perform a combined optimization of strategic, behavioral, and kinematic features. The specification and tuning of a…

Trajectory Planning