9 papers
Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces
Jiayuan Du, Yuebing Song, Yiming Zhao +6
End-to-End autonomous driving (E2E-AD) systems face challenges in lifelong learning, including catastrophic forgetting, difficulty in knowledge transfer across diverse scenarios, a…
TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition
Minghao Zhu, Xiao Lin, Mengxian Hu +5
Adapting CLIP for open-vocabulary video recognition necessitates a delicate balance between newly acquired video knowledge and the pretrained generalization. While existing studies…
KinematicRL: A Sim-to-Real Reinforcement Learning Framework For Social Navigation With Kinodynamic Feasibility
Zhiming Xu, Haodong Yang, Chengju Liu +2
Deep Reinforcement Learning (DRL) has shown promise for social navigation, yet its real-world deployment remains hindered by a persistent sim-to-real gap arising from simplified fi…
Dynamics Are Learned, Not Told: Semi-Supervised Discovery of Latent Dynamics Geometries For Zero-Shot Policy Adaptation
Zhiming Xu, Weitao Zhou, Xianghui Pan +4
Real-world dynamics shifts pose a critical challenge for reinforcement learning in robotics, as policies tightly coupled to nominal environments often fail catastrophically when ph…
P2DNav: Panorama-to-Downview Reasoning for Zero-shot Vision-and-Language Navigation
Kai Sheng, Liuyi Wang, Haojie Dai +5
Vision-and-language navigation (VLN) requires an embodied agent to ground natural-language instructions into executable navigation actions in unseen environments. Existing zero-sho…
CLASH: Collaborative Large-Small Hierarchical Framework for Continuous Vision-and-Language Navigation
Liuyi Wang, Zongtao He, Jinlong Li +6
Vision-and-Language Navigation (VLN) requires robots to follow natural language instructions and navigate complex environments without prior maps. While recent vision-language larg…