4 citations · 17 across the 8 of their papers we have counts for
8 papers
ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination
Teng Wang, Xinxin Zhao, Wenzhe Cai +1
Visual navigation is a fundamental capability for autonomous home-assistance robots, enabling long-horizon tasks such as object search. While recent methods have leveraged Large La…
ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination
Xinxin Zhao, Wenzhe Cai, Likun Tang +1
Visual navigation is an essential skill for home-assistance robots, providing the object-searching ability to accomplish long-horizon daily tasks. Many recent approaches use Large…
Empowering Large Language Models on Robotic Manipulation with Affordance Prompting
Guangran Cheng, Chuheng Zhang, Wenzhe Cai +3
While large language models (LLMs) are successful in completing various language processing tasks, they easily fail to interact with the physical world by generating control sequen…
XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library
Wenzhang Liu, Wenzhe Cai, Kun Jiang +7
In this paper, we present XuanCe, a comprehensive and unified deep reinforcement learning (DRL) library designed to be compatible with PyTorch, TensorFlow, and MindSpore. XuanCe of…
DGMem: Learning Visual Navigation Policy without Any Labels by Dynamic Graph Memory
Wenzhe Cai, Teng Wang, Guangran Cheng +2
In recent years, learning-based approaches have demonstrated significant promise in addressing intricate navigation tasks. Traditional methods for training deep neural network navi…
Robust Navigation with Cross-Modal Fusion and Knowledge Transfer
Wenzhe Cai, Guangran Cheng, Lingyue Kong +2
Recently, learning-based approaches show promising results in navigation tasks. However, the poor generalization capability and the simulation-reality gap prevent a wide range of a…
Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skill
Wenzhe Cai, Siyuan Huang, Guangran Cheng +4
Zero-shot object navigation is a challenging task for home-assistance robots. This task emphasizes visual grounding, commonsense inference and locomotion abilities, where the first…
Biasing Like Human: A Cognitive Bias Framework for Scene Graph Generation
Xiaoguang Chang, Teng Wang, Changyin Sun +1
Scene graph generation is a sophisticated task because there is no specific recognition pattern (e.g., "looking at" and "near" have no conspicuous difference concerning vision, whe…