Yuke Qu

Autonomous Obstacle Traversal Method for Tracked Robots Based on Hierarchical Reinforcement Learning

Hongchuan Zhang, Junkai Ren, Yuke Qu, Hainan Pan et autres

cn (code pays fourni par la source)

Efficient Long-Horizon Mobile Manipulation with RAG-Assisted Vision Language Models

Yuxuan Han, Yuke Qu, Junkai Ren, Ming Xu et autres

In dynamic and complex real-world environments, long-horizon mobile manipulation tasks impose higher demands on the autonomous capabilities of robots. Traditional methods suffer from poor generalization and high data requirements. This paper proposes a task planning method called Retrieval-Augmented generation-assisted Vision-Language Model (RAVLM). …

cn (code pays fourni par la source)

Graph Reinforcement Learning-Based Reachability Map for Generalized Mobile Manipulation

Junkai Ren, Zhiqian Zhou, Yuke Qu, Huimin Lu et autres

Mobile manipulators need to determine feasible navigation positions before manipulation tasks. Real-world environments, with varying obstacles and objects, pose significant challenges for computing optimal navigation positions due to their variability. In this work, a novel method namedGraphReinforcement Learning-based ReachabilityMap (GRAM) is proposed. …

cn (code pays fourni par la source)

PhyTransformer: A unified framework for learning spatial–temporal representation from physiological signals

Hongxin Li, Yaru Liu, Yuke Qu, Wei Dai et autres

cn (code pays fourni par la source)

State Space Sampling for Adaptive Path Planning in Outdoor Unstructured Environments

Jiang Lu, Jiayang Liu, Jiawei Luo, Yuke Qu et autres

This paper addresses the challenges faced by autonomous ground robot navigation in unstructured outdoor environments. Traditional control space sampling methods lack task orientation and may lead to collisions. This paper proposed a state space sampling-based path planning method. The method takes the …

cn (code pays fourni par la source)

Hierarchical Task Scheduling and Robotic Manipulation for Autonomous Materials Discovery

Jiang Lu, Junkai Ren, Yuke Qu, Jiawei Luo et autres

The use of mobile manipulator (MM) in materials laboratories remains limited due to several key challenges, including the difficulty for non-expert users to control the MM using natural language instructions and the difficulty for MM to execute long-horizon tasks. As a result, …

cn (code pays fourni par la source)

Bidirectional temporal feature for 3D human pose and shape estimation from a video

Libo Sun, Ting Tang, Yuke Qu, Wenhu Qin

Abstract 3D human pose and shape estimation is the foundation of analyzing human motion. However, estimating accurate and temporally consistent 3D human motion from a video remains a challenge. By now, most of the video‐based methods for estimating 3D human pose and …

cn (code pays fourni par la source)

Crowd navigation in an unknown and complex environment based on deep reinforcement learning

Libo Sun, Yuke Qu, Wenhu Qin

Abstract We propose a virtual crowd navigation approach based on deep reinforcement learning to improve the adaptability of virtual crowds in an unknown and complex environment. To address the problem of local optimum or slow iteration or even failure to converge due …

cn (code pays fourni par la source)

Attention-Based Context Aware Network for Semantic Comprehension of Aerial Scenery

Weipeng Shi, Wenhu Qin, Zhonghua Yun, Peng Ping et autres

It is essential for researchers to have a proper interpretation of remote sensing images (RSIs) and precise semantic labeling of their component parts. Although FCN (Fully Convolutional Networks)-like deep convolutional network architectures have been widely applied in the perception of autonomous cars, …

cn (code pays fourni par la source)