Publications

IROS 2026

APPLV: Adaptive Planner Parameter Learning from Vision-Language-Action Model
Y. Lu, B. Wang, Z. Wu, Y. Li, X. Lin, C. Mao, X. Xiao — Submitted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026 Leverages a vision-language-action model to predict navigation planner parameters rather than actions directly. | paper

IROS 2026

Moving Through Clutter: Scaling Data Collection and Benchmarking for 3D Scene-Aware Humanoid Locomotion via Virtual Reality
B. Wang, Y. Lu, L. Wang, L Yu, X. Xiao — Submitted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026 Generates scenes with controllable clutter levels and captures embodiment-consistent, whole-body human motion through immersive VR navigation. | paper

IROS 2026

CORAL: COntextual Reasoning And Local Planning in A Hierarchical VLM Framework for Underwater Monitoringn
Z. Wu, Y. Lu, X. Xiao, X. Lin — Submitted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026 A framework that decouples high-level semantic reasoning from low-level reactive control. | paper

ICRA 2026

Adaptive Dynamics Planning for Robot Navigation
Y. Lu, M. Mao, T. Xu, L. Wang, X. Lin, X. Xiao — IEEE International Conference on Robotics and Automation (ICRA), 2026 Integrates adaptive dynamics modeling with learning-based local planners for efficient navigation in constrained environments. | paper

IROS 2025

Decremental Dynamics Planning for Robot Navigation
Y. Lu, T. Xu, L. Wang, N. Hawes, X. Xiao — IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025 Hierarchical dynamic reconfiguration enabling real-time replanning. | paper | video

IROS 2025

Reward Training Wheels: Adaptive Auxiliary Rewards for Robotics Reinforcement Learning
L. Wang, T. Xu, Y. Lu, X. Xiao — IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025 Adaptive auxiliary reward shaping that phases out to avoid policy degradation. | paper | video

RSS 2025

Verti-Bench: A General and Scalable Off-Road Mobility Benchmark for Vertically Challenging Terrain
T. Xu, C. Pan, M. B. Rao, A. Datar, A. Pokhrel, Y. Lu, X. Xiao — Robotics: Science and Systems, 2025 Benchmark for vertical mobility across heterogeneous terrain profiles. | paper | video

ICRA 2025

Autonomous Ground Navigation in Highly Constrained Spaces: Lessons Learned from the Fourth BARN Challenge at ICRA 2025
X. Xiao, Z. Xu, S. A. Ghani, A. Datar, D. Song, P. Stone, K. Yazdipaz, Y. Lu, … — IEEE International Conference on Robotics and Automation (ICRA), 2025 (Competition Track) Report and analysis from large-scale constrained-space navigation benchmarking. | paper | website

ICRA 2025

Multi-goal motion memory
Y. Lu, D. Das, E. Plaku, X. Xiao — IEEE International Conference on Robotics and Automation (ICRA), 2025 Experience reuse via CNN-based path priors to speed up planning. | paper | video

ICRA 2024

Motion Memory: Leveraging Past Experiences to Accelerate Future Motion Planning
D. Das, Y. Lu, E. Plaku, X. Xiao — IEEE International Conference on Robotics and Automation (ICRA), 2024 Experience reuse via CNN-based path priors to speed up planning. | paper | video

IROS 2023

Leveraging Single-goal Predictions to Improve the Efficiency of Multi-goal Motion Planning with Dynamics
Y. Lu, E. Plaku — IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023 Single-goal predictors as priors to accelerate multi-goal planning with dynamics. | paper | video

IROS 2022

Improving the Efficiency of Sampling-based Motion Planners via Runtime Predictions for Motion-planning Problems with Dynamics
H. D. Bui, Y. Lu, E. Plaku — IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022 Runtime predictions informing sampling-based planning under dynamics. | paper | video

BIBM 2021

Deep Latent-variable Models for Controllable Molecule Generation
Y. Du, Y. Wang, F. Alam, Y. Lu, X. Guo, L. Zhao, A. Shehu — IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2021 Controllable molecule generation via latent-variable models. | paper

Yuanjie Lu

Publications