← Search

Zongyuan Zhang

6 accepted papers

2026

NSC-SL: A Bandwidth-Aware Neural Subspace Compression for Communication-Efficient Split Learning

ICASSP 2026poster

The expanding scale of neural networks poses a major challenge for distributed machine learning, particularly under limited communication resources. While split learning (SL) alleviates client computational burden by distributing model layers between clients and server, it incurs substantial communi…

Cited by 0SourcePDFScholar
2025

Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective

ICASSP 2025accepted

Deep Reinforcement Learning (DRL) suffers from uncertainties and inaccuracies in the observation signal in real-world applications. Adversarial attack is an effective method for evaluating the robustness of DRL agents. However, existing attack methods targeting individual sampled actions have limite…

Cited by 16SourceScholar
2025

Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks

IROS 2025

Deep reinforcement learning (DRL) has emerged as a promising approach for robotic control, but its real-world deployment remains challenging due to its vulnerability to environmental perturbations. Existing white-box adversarial attack methods, adapted from supervised learning, fail to effectively t

Cited by 12SourceScholar
2024

AGRNav: Efficient and Energy-Saving Autonomous Navigation for Air-Ground Robots in Occlusion-Prone Environments

ICRA 2024poster

The exceptional mobility and long endurance of air-ground robots are raising interest in their usage to navigate complex environments (e.g., forests and large buildings). However, such environments often contain occluded and unknown regions, and without accurate prediction of unobserved obstacles, t…

Cited by 6SourcecodeScholar
2024

HE-Nav: A High-Performance and Efficient Navigation System for Aerial-Ground Robots in Cluttered Environments

RA-L 2024

Existing AGR navigation systems have advanced in lightly occluded scenarios (e.g., buildings) by employing 3D semantic scene completion networks for voxel occupancy prediction and constructing Euclidean Signed Distance Field (ESDF) maps for collision-free path planning. However, these systems exhibi

Cited by 6SourceScholar