← Search

Huaicheng Yan

7 accepted papers

2026

From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Tracking

CVPR 2026

End-to-end multi-object tracking (MOT) methods have recently achieved remarkable progress by unifying detection and association within a single framework. Despite their strong detection performance, these methods suffer from relatively low association accuracy. Through detailed analysis, we observe

Cited by 0SourcecodeScholar
2026

RHCNet: Residual-Guided Hierarchical Calibration Network for Robust Underwater Object Detection

CVPR 2026

Underwater images commonly suffer from foreground-background ambiguity, loss of structural details, and severely reduced contrast, which collectively make underwater object detection (UOD) an inherently challenging task. To handle this issue, we present a residual-guided hierarchical calibration net

Cited by 0SourcecodeScholar
2026

Safe Multi-Agent Reinforcement Learning via Distributional Safety Critic and Maximum Entropy Optimization

AAAI 2026technical

Deploying multi-agent reinforcement learning (MARL) in safety-critical systems faces significant challenges due to insufficient agent exploration and inadequate safety constraint guarantees. Current approaches are constrained by two fundamental limitations: inefficient exploration leading to subopti

Cited by 0SourcePDFScholar
2025

DistillDrive: End-to-End Multi-Mode Autonomous Driving Distillation by Isomorphic Hetero-Source Planning Model

ICCV 2025poster

End-to-end autonomous driving has been recently seen rapid development, exerting a profound influence on both industry and academia. However, the existing work places excessive focus on ego-vehicle status as their sole learning objectives and lacks of planning-oriented understanding, which limits th…

2025

Distributed Pursuit of an Evader with Adaptive Robust Path Control Under State Measurement Uncertainty

ICRA 2025

This paper presents a distributed pursuit frame-work for environments with obstacles considering state measurement uncertainty. Our framework consists of two primary components: the computation of safe pursuit regions based on Voronoi cell (VC) and the solution of an adaptive robust path controller

Cited by 0SourceScholar
2025

Swift Pursuer: A Topology-Accelerated and Robust Approach for Pursuing an Evader in Obstacle Environments With State Measurement Uncertainty

RA-L 2025

This letter presents a topology-accelerated and robust pursuit framework for environments with obstacles considering state measurement uncertainty. Our framework consists of three primary components: the selection of virtual target points using topological heuristic method to encourage path diversit

Cited by 9SourceScholar
2024

Quaternion-Based Optimal Interpolation of Similarity Transformations for Multi-Agent Formation

RA-L 2024

This paper addresses the challenge of optimal motion interpolation in multi-agent formation control. The primary goal is to generate trajectories of similarity transformations that minimize various metrics, such as distance traveled, kinetic energy consumption, and overall smoothness. The quaternion

Cited by 2SourceScholar