20 papers
VP-EVT: Active Visibility Preservation for Embodied Visual Tracking
Yanci Wen, Tianle Zeng, Jianwei Peng +3
Embodied Visual Tracking (EVT) is an essential capability for intelligent robots in human-robot collaboration, requiring an agent to follow a designated target person in dynamic en…
Graph3R: Unifying View Graph Initialization with Feed-Forward Reconstruction
Jingwen Yu, Hengli Wang, Jianhao Jiao +3
Feed-forward reconstruction recovers camera poses and dense geometry from image sets whose views are assumed to come from a single scene. In practice, uncurated image collections o…
Traj-VLN: Learning Pixel-Space Interaction via Autoregressive Trajectory Generation
Changfei Fu, Guangcheng Chen, Aoxiang Gu +3
Benefiting from the powerful priors embedded in large-scale pre-training data and the emerging commonsense reasoning ability, large language models (LLMs) have shown unprecedented…
HAM-VLN: Harnessing Hierarchical Agentic Memory for Zero-Shot Vision-and-Language Navigation
An Liu, Bingxi Liu, Hongyu Ding +6
Vision-and-language navigation (VLN) enables robots to follow instructions in previously unseen environments. Recently, a training-free paradigm has emerged: the robot queries a mu…
ReferTrack: Referring Then Tracking for Embodied Visual Tracking
Hanjing Ye, Tianle Zeng, Jiazhao Zhang +6
Embodied visual tracking (EVT) requires a mobile agent to continuously follow a specific target described in natural language using only onboard vision. While recent vision-languag…
Can Single-View Mesh Reconstruction Generalize to Robot Camera Rotation?
Yu Zhan, Guangcheng Chen, Hanjing Ye +4
Single-view mesh reconstruction predicts object meshes and spatial layouts from a single observation, making it attractive for fast robot spatial reasoning and real-to-sim digital…
TARIC: Memory-Augmented Traversability-Aware Outdoor VLN under Interrupted Semantic Cues
Tianle Zeng, Hanjing Ye, Jianwei Peng +3
Outdoor vision-language navigation (VLN) in long-range, open-world environments is frequently disrupted by semantic-cue interruptions, where informative goal cues become sparse, oc…
Can Aerial VLA Models Cooperate? Evaluating Closed-Loop Air-Ground Coordination with CARLA-Air
Tianle Zeng, Yanci Wen, Xueang Yu +1
Recent aerial vision-language-action (VLA) models show promising single-UAV capabilities, such as tracking moving objects and navigating to language-specified landmarks. However, i…
Adap-RPF: Adaptive Trajectory Sampling for Robot Person Following in Dynamic Crowded Environments
Weixi Situ, Hanjing Ye, Jianwei Peng +2
Robot person following (RPF) is a core capability in human-robot interaction, enabling robots to assist users in daily activities, collaborative work, and other service scenarios.…
TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
Jiahang Liu, Yunpeng Qi, Jiazhao Zhang +9
Embodied Visual Tracking (EVT) is a fundamental ability that underpins practical applications, such as companion robots, guidance robots and service assistants, where continuously…
Meta-Memory: Retrieving and Integrating Semantic-Spatial Memories for Robot Spatial Reasoning
Yufan Mao, Hanjing Ye, Wenlong Dong +2
Navigating complex environments requires robots to effectively store observations as memories and leverage them to answer human queries about spatial locations, which is a critical…
EZREAL: Enhancing Zero-Shot Outdoor Robot Navigation toward Distant Targets under Varying Visibility
Tianle Zeng, Jianwei Peng, Hanjing Ye +3
Zero-shot object navigation (ZSON) in large-scale outdoor environments faces many challenges; we specifically address a coupled one: long-range targets that reduce to tiny projecti…
Follow-Bench: A Unified Motion Planning Benchmark for Socially-Aware Robot Person Following
Hanjing Ye, Weixi Situ, Jianwei Peng +4
Robot person following (RPF) -- mobile robots that follow and assist a specific person -- has emerging applications in personal assistance, security patrols, eldercare, and logisti…
GraphCoT-VLA: A 3D Spatial-Aware Reasoning Vision-Language-Action Model for Robotic Manipulation with Ambiguous Instructions
Helong Huang, Min Cen, Kai Tan +3
Vision-language-action models have emerged as a crucial paradigm in robotic manipulation. However, existing VLA models exhibit notable limitations in handling ambiguous language in…
TPT-Bench: A Large-Scale, Long-Term and Robot-Egocentric Dataset for Benchmarking Target Person Tracking
Hanjing Ye, Yu Zhan, Weixi Situ +6
Tracking a target person from robot-egocentric views is crucial for developing autonomous robots that provide continuous personalized assistance or collaboration in Human-Robot Int…
FlowPlan: Zero-Shot Task Planning with LLM Flow Engineering for Robotic Instruction Following
Zijun Lin, Chao Tang, Hanjing Ye +1
Robotic instruction following tasks require seamless integration of visual perception, task planning, target localization, and motion execution. However, existing task planning met…
Monocular Person Localization under Camera Ego-motion
Yu Zhan, Hanjing Ye, Hong Zhang
Localizing a person from a moving monocular camera is critical for Human-Robot Interaction (HRI). To estimate the 3D human position from a 2D image, existing methods either depend…
RPF-Search: Field-based Search for Robot Person Following in Unknown Dynamic Environments
Hanjing Ye, Kuanqi Cai, Yu Zhan +3
Autonomous robot person-following (RPF) systems are crucial for personal assistance and security but suffer from target loss due to occlusions in dynamic, unknown environments. Cur…
GV-Bench: Benchmarking Local Feature Matching for Geometric Verification of Long-term Loop Closure Detection
Jingwen Yu, Hanjing Ye, Jianhao Jiao +2
Visual loop closure detection is an important module in visual simultaneous localization and mapping (SLAM), which associates current camera observation with previously visited pla…
Human Orientation Estimation under Partial Observation
Jieting Zhao, Hanjing Ye, Yu Zhan +2
Reliable Human Orientation Estimation (HOE) from a monocular image is critical for autonomous agents to understand human intention. Significant progress has been made in HOE under…