Papers
86
Total Citations
1,864
H-Index
26
About
Xuesu Xiao is a prominent robotics researcher whose work sits at the intersection of mobile robot navigation, machine learning, and human-robot interaction. Best known for his sweeping survey on machine learning for robot motion planning and control (234 citations), Xiao has systematically advanced how autonomous robots learn to navigate complex, real-world environments. His research spans adaptive navigation frameworks — including the influential APPLD and APPL systems — that enable robots to tune their own parameters from human demonstrations rather than relying on expert reconfiguration, dramatically lowering deployment barriers. Xiao has made significant strides in social robot navigation, contributing the large-scale SCAND dataset (101 citations) and co-authoring community-wide evaluation principles to standardize how social navigation algorithms are assessed. His lifelong learning framework (97 citations) addresses the critical challenge of robots that improve continuously rather than repeating failures. Beyond ground robots, his work extends to off-road terrain navigation, agile maneuvering in constrained spaces, and even tethered UAV indoor localization. With a consistently high-impact publication record exceeding 800 cumulative citations across just ten works, Xiao represents a leading voice shaping the future of intelligent, adaptable, and socially aware autonomous navigation.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3A Lifelong Learning Approach to Mobile Robot Navigation97 citations · 2021
- 4APPLD: Adaptive Planner Parameter Learning From Demonstration66 citations · 2020
- 5
- 6Principles and Guidelines for Evaluating Social Robot Navigation Algorithms59 citations · 2024
- 7Indoor UAV Localization Using a Tether55 citations · 2018
- 8
- 9APPL: Adaptive Planner Parameter Learning43 citations · 2022
- 10VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigation42 citations · 2022