Aim My Robot: Precision Local Navigation to Any Object
- 14 February 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (4) , 3707-3714
Abstract
Existing navigation systems mostly consider “success” when the robot reaches within 1 m radius to a goal. This precision is insufficient for emerging applications where a robot needs to be positioned precisely relative to an object for downstream tasks, such as docking, inspection, and manipulation. To this end, we design and implement Aim-My-Robot (AMR), a local navigation system that enables a robot to reach any object in its vicinity at the desired relative pose, with centimeter-level accuracy. AMR achieves high accuracy and robustness by leveraging multi-modal sensors, precise action prediction, and is trained on large-scale photorealistic data generated in simulation. AMR shows strong sim2real transfer and can adapt to different robot kinematics and unseen objects with little to no fine-tuning.Keywords
All Related Versions
Funding Information
- NVIDIA and Accenture
This publication has 27 references indexed in Scilit:
- SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World2024
- SPIN: Simultaneous Perception, Interaction and Navigation2024
- SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation2024
- FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects2024
- Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation2024
- Navigating to Objects Specified by Images2023
- Skill Transformer: A Monolithic Policy for Mobile Manipulation2023
- Segment Anything2023
- Masked Autoencoders Are Scalable Vision Learners2022
- A path following control of an unmanned autonomous forkliftInternational Journal of Control, Automation, and Systems, 2009