Qingbiao Li
University of Cambridge
29 Papers
30 Citations
Qingbiao Li is an academic researcher from University of Cambridge. The author has contributed to research in topics: Computer science & Motion planning. The author has an hindex of 6, co-authored 22 publications. Previous affiliations of Qingbiao Li include Imperial College London.
Chat about Author
Papers
Mobile Robot Path Planning in Dynamic Environments Through Globally Guided Reinforcement Learning
Binyu Wang,Zhe Liu,Qingbiao Li,Amanda Prorok +3 more
- 24 Sep 2020
TL;DR: This work introduces a globally guided reinforcement learning approach (G2RL), which incorporates a novel reward structure that generalizes to arbitrary environments and applies G2RL to solve the multi-robot path planning problem in a fully distributed reactive manner.
273
Graph Neural Networks for Decentralized Multi-Robot Path Planning
Qingbiao Li,Fernando Gama,Alejandro Ribeiro,Amanda Prorok +3 more
- 24 Oct 2020
TL;DR: In this article, a combined model that automatically synthesizes local communication and decision-making policies for robots navigating in constrained workspaces is proposed, which is composed of a CNN that extracts adequate features from local observations, and a graph neural network (GNN) that communicates these features among robots.
207
•Posted Content
Graph Neural Networks for Decentralized Multi-Robot Path Planning
TL;DR: A combined model is proposed that automatically synthesizes local communication and decision-making policies for robots navigating in constrained workspaces that shows its capability to generalize to previously unseen cases.
153
Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning
Qingbiao Li,Weizhe Lin,Zhe Liu,Amanda Prorok +3 more
- 05 May 2021
TL;DR: MAGAT as mentioned in this paper is based on a key-query-like mechanism that determines the relative importance of features in the messages received from various neighboring robots, and it achieves a performance close to that of a coupled centralized expert algorithm.
114
•Posted Content
Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning
TL;DR: The Message-Aware Graph Attention neTwork (MAGAT) is based on a key-query-like mechanism that determines the relative importance of features in the messages received from various neighboring robots and is able to achieve a performance close to that of a coupled centralized expert algorithm.
88