6 papers
TGSFormer: Scalable Temporal Gaussian Splatting for Embodied Semantic Scene Completion
Rui Qian, Haozhi Cao, Tianchen Deng +4
Embodied 3D Semantic Scene Completion (SSC) infers dense geometry and semantics from continuous egocentric observations. Most existing Gaussian-based methods rely on random initial…
STARC: See-Through-Wall Augmented Reality Framework for Human-Robot Collaboration in Emergency Response
Shenghai Yuan, Weixiang Guo, Tianxin Hu +5
In emergency response missions, first responders must navigate cluttered indoor environments where occlusions block direct line-of-sight, concealing both life-threatening hazards a…
Energy-Constrained Navigation for Planetary Rovers under Hybrid RTG-Solar Power
Tianxin Hu, Weixiang Guo, Ruimeng Liu +5
Future planetary exploration rovers must operate for extended durations on hybrid power inputs that combine steady radioisotope thermoelectric generator (RTG) output with variable…
PERAL: Perception-Aware Motion Control for Passive LiDAR Excitation in Spherical Robots
Shenghai Yuan, Jason Wai Hao Yee, Weixiang Guo +3
Autonomous mobile robots increasingly rely on LiDAR-IMU odometry for navigation and mapping, yet horizontally mounted LiDARs such as the MID360 capture few near-ground returns, lim…
CETUS: Causal Event-Driven Temporal Modeling With Unified Variable-Rate Scheduling
Hanfang Liang, Bing Wang, Shizhen Zhang +4
Event cameras capture asynchronous pixel-level brightness changes with microsecond temporal resolution, offering unique advantages for high-speed vision tasks. Existing methods oft…
CleanUpBench: Embodied Sweeping and Grasping Benchmark
Wenbo Li, Guanting Chen, Tao Zhao +5
Embodied AI benchmarks have advanced navigation, manipulation, and reasoning, but most target complex humanoid agents or large-scale simulations that are far from real-world deploy…