DeepAI AI Chat
Log In Sign Up

LeTS-Drive: Driving in a Crowd by Learning from Tree Search

by   Panpan Cai, et al.

Autonomous driving in a crowded environment, e.g., a busy traffic intersection, is an unsolved challenge for robotics. The robot vehicle must contend with a dynamic and partially observable environment, noisy sensors, and many agents. A principled approach is to formalize it as a Partially Observable Markov Decision Process (POMDP) and solve it through online belief-tree search. To handle a large crowd and achieve real-time performance in this very challenging setting, we propose LeTS-Drive, which integrates online POMDP planning and deep learning. It consists of two phases. In the offline phase, we learn a policy and the corresponding value function by imitating the belief tree search. In the online phase, the learned policy and value function guide the belief tree search. LeTS-Drive leverages the robustness of planning and the runtime efficiency of learning to enhance the performance of both. Experimental results in simulation show that LeTS-Drive outperforms either planning or imitation learning alone and develops sophisticated driving skills.


page 1

page 6

page 8


Closing the Planning-Learning Loop with Application to Autonomous Driving in a Crowd

Imagine an autonomous robot vehicle driving in dense, possibly unregulat...

DESPOT: Online POMDP Planning with Regularization

The partially observable Markov decision process (POMDP) provides a prin...

Towards Using Fully Observable Policies for POMDPs

Partially Observable Markov Decision Process (POMDP) is a framework appl...

Bi-directional Value Learning for Risk-aware Planning Under Uncertainty

Decision-making under uncertainty is a crucial ability for autonomous sy...

Anytime Game-Theoretic Planning with Active Reasoning About Humans' Latent States for Human-Centered Robots

A human-centered robot needs to reason about the cognitive limitation an...

Multi-Resolution POMDP Planning for Multi-Object Search in 3D

Robots operating in household environments must find objects on shelves,...

Online POMDP Planning via Simplification

In this paper, we consider online planning in partially observable domai...