INSPECT: Learning Robot View Selection from Assistant Use
cs.RO, cs.CV
Submitted: 2026-09-17
Updated: 2026-09-17
Code: https://github.com/Kratos-Wen/INSPECT
Terminology
Sources
- Toward Ambulatory Vision: Learning Visually-Grounded Active View Selection
- ActiveMimic: Egocentric Video Pretraining with Active Perception
- LIME: Learning Intent-aware Camera Motion from Egocentric Video
- IMPACT: A Dataset for Multi-Granularity Human Procedural Action Understanding in Industrial Assembly
- Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges
- Plan, Watch, Recover: A Benchmark and Architectures for Proactive Procedural Assistance
- Hierarchical Policies from Verbal and Egocentric Human Signals for Natural Human-Robot Interaction
- ActiveUMI: Robotic Manipulation with Active Perception from Robot-Free Human Demonstrations
- OA-NBV: Occlusion-Aware Next-Best-View Planning for Human-Centered Active Perception on Mobile Robots
- Scene Exploration by Vision-Language Models
- Robot Planning and Situation Handling with Active Perception
- Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models
- BoT-SORT: Robust Associations Multi-Pedestrian Tracking
- Qwen3-VL Technical Report
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving