DDPG car-following model with real-world human driving experience in CARLA

12/29/2021
by   Dianzhao Li, et al.
0

In the autonomous driving field, the fusion of human knowledge into Deep Reinforcement Learning (DRL) is often based on the human demonstration recorded in the simulated environment. This limits the generalization and the feasibility of application in real-world traffic. We proposed a two-stage DRL method, that learns from real-world human driving to achieve performance that is superior to the pure DRL agent. Training a DRL agent is done within a framework for CARLA with Robot Operating System (ROS). For evaluation, we designed different real-world driving scenarios to compare the proposed two-stage DRL agent with the pure DRL agent. After extracting the 'good' behavior from the human driver, such as anticipation in a signalized intersection, the agent becomes more efficient and drives safer, which makes this autonomous agent more adapt to Human-Robot Interaction (HRI) traffic.

READ FULL TEXT
research
04/14/2023

A Platform-Agnostic Deep Reinforcement Learning Framework for Effective Sim2Real Transfer in Autonomous Driving

Deep Reinforcement Learning (DRL) has shown remarkable success in solvin...
research
03/22/2021

Enhancing the Generalization Performance and Speed Up Training for DRL-based Mapless Navigation

Training an agent to navigate with DRL is data-hungry, which requires mi...
research
05/19/2023

Vision-based DRL Autonomous Driving Agent with Sim2Real Transfer

To achieve fully autonomous driving, vehicles must be capable of continu...
research
02/02/2020

Integrating Deep Reinforcement Learning with Model-based Path Planners for Automated Driving

Automated driving in urban settings is challenging chiefly due to the in...
research
07/03/2023

Towards Safe Autonomous Driving Policies using a Neuro-Symbolic Deep Reinforcement Learning Approach

The dynamic nature of driving environments and the presence of diverse r...
research
09/22/2021

ENERO: Efficient Real-Time Routing Optimization

Wide Area Networks (WAN) are a key infrastructure in today's society. Du...
research
02/10/2020

Proficiency Aware Multi-Agent Actor-Critic for Mixed Aerial and Ground Robot Teaming

Mixed Cooperation and competition are the actual scenarios of deploying ...

Please sign up or login with your details

Forgot password? Click here to reset