MIGU: Multimodal Instruction Grounding under Uncertainty for Manipulation Planning
cs.RO
Submitted: 2026-09-21
Updated: 2026-09-21
Terminology
Sources
- Tell and show: Combining multiple modalities to communicate manipulation tasks to a robot
- Qwen3-VL Technical Report
- Gemini Robotics: Bringing AI into the Physical World
- Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
- PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs
- MediaPipe Hands: On-device Real-time Hand Tracking
- Visibility-Aware Mobile Grasping in Dynamic Environments
- cuRoboV2: Dynamics-Aware Motion Generation with Depth-Fused Distance Fields for High-DoF Robots
- Understanding Embodied Reference with Touch-Line Transformer
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