← Search

Le Zheng

4 accepted papers

2026

Fisher-Preserving Guidance: Training-Free Manifold Constraints for Safe Diffusion Control

ICML 2026poster

Diffusion models are effective for waypoint prediction in visual navigation, but standard sampling and test time guidance can produce unsafe or inefficient trajectories when updates drift off the training manifold. We propose Fisher Preserving Guidance with Outer Product Span Projection, a training-…

Cited by 0SourceScholar
2026

SR-Planner: Sampling-Based Path Planning With Feasibility-Aware Focus Regions and Robust Trajectory Optimization for Mobile Manipulator

RA-L 2026

High-quality motion planning for mobile manipulators remains a challenging task due to the high dimensionality and complex constraints involved. While existing methods perform well in specific scenarios, their efficiency and the quality of the resulting paths and trajectories often degrade in dense

Cited by 0SourceScholar
2025

RM-Planner: Integrating Reinforcement Learning with Whole-Body Model Predictive Control for Mobile Manipulation

ICRA 2025

Mobile manipulation is a crucial problem in various real-world applications. However, existing methods have demonstrated unsatisfactory training efficiency and sparse rewards, requiring complex coordination strategies between the mobile base and arm. In this paper, we propose RM-Planner, a planning

Cited by 3SourcecodeScholar
2023

Doppler-Coded Joint Division Multiple Access Waveform for Automotive MIMO Radar

ICASSP 2023accepted

Slow-time coded waveforms are commonly used in automotive multiple-input multiple-output (MIMO) radar to achieve inter-channel spatial diversity. Typical waveforms, such as Doppler division multiple access (DDMA) and code division multiple access (CDMA), are known to suffer from Doppler ambiguity an…

Cited by 0SourceScholar