NVIDIA Introduces COMPASS Framework to Enhance Robot Navigation Learning
- Published
- Source
- InterestingEngineering.com
Researchers have developed NVIDIA's new framework, COMPASS, aimed at simplifying the training of robot navigation systems across various machines and environments. This innovative approach combines AI agents, simulation, reinforcement learning, and automated testing to significantly reduce the time and effort required to adapt navigation policies when changes occur in robots, scenes, or operating conditions.
The importance of COMPASS lies in its ability to streamline the development process for robot navigation, which is inherently complex. Traditional methods often require extensive data collection and retraining when robots or environments change. By leveraging a pretrained navigation model and reinforcement learning, COMPASS allows developers to adapt existing policies rather than starting from scratch, thus minimizing workload and improving efficiency.
Looking ahead, developers can utilize COMPASS with robots like the Boston Dynamics Spot quadruped, testing in both built-in and complex environments. The framework's integration with NVIDIA’s SAGE-10K dataset and Omniverse NuRec for realistic simulations will be crucial for fine-tuning navigation policies. No further timeline was disclosed at the time of publication.
Original report
New NVIDIA framework could help robots learn to move through new places
InterestingEngineering.com · Jijo MalayilThis briefing is an independently written summary based on publicly available reporting and is provided for industry information and news discovery. The original report and source publication are credited and linked where applicable. RobotToday does not claim ownership of third-party source material.
Rights concerns? Contact [email protected] with the relevant URL and details. We will review the matter and take appropriate action where warranted.
More related news
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
Related Suppliers
NVIDIA Robotics
United States
NVIDIA robotics division delivering Isaac simulation and training tools, Jetson edge compute modules, and Omniverse digital twin frameworks for physical AI.
Deci AI (Acquired by NVIDIA)
Israel
Israeli deep learning optimization startup acquired by NVIDIA in May 2024 for ~$300M; known for AutoNAC neural architecture search technology.
CompassDrone
United States
Denver-based drone solutions provider offering hardware, LiDAR, software, FAA Part 107 training, and geospatial data services for mapping professionals.
AALTO
United Kingdom
Farnborough, UK Airbus subsidiary founded 2022 that builds and flies the solar-electric Zephyr HAPS drone; holds a 67-day stratospheric flight record.
Tangent Robotics
United States
New York City spin-out of Columbia Engineering building tactile multi-finger robot hands and learned dexterity policies; raised a 4.5M pre-seed round in 2026.
AI, Data and Robotics Association (Adra, asbl)
Belgium
European public-private partnership association driving AI, data, and robotics research and innovation under Horizon Europe.
Sage Automation
Australia
Adelaide, Australia automation integrator founded 1994 by Andrew Downs; SAGE Group, its parent, was acquired by Tetra Tech in 2025 with about 800 staff.
Black Sage Technologies
United States
Counter-UAS technology and AI-driven command and control solutions for military and critical infrastructure protection.
Accenture
Ireland
Dublin-based global consulting giant offering robotics integration, AI orchestration, and automation services across manufacturing, logistics, and healthcare.
TRON K.K.
Japan
Tokyo humanoid integrator (est. 2024) bringing physical-AI robots, simulation training and Prevu3D factory digital twins to Japanese manufacturers.
SyboTech
Russian Federation
Moscow-based robotics startup (est. 2013) developing RNS autonomous navigation software for service robots, AGVs, and educational platforms.
Marvelmind Robotics
United States
Developer of high-precision indoor positioning systems using ultrasonic beacons for autonomous robots, AGVs, and drones.
Robotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
Join the RobotToday community on LinkedIn
Daily robotics news, in-depth analysis, conference highlights, and discussions with professionals worldwide.
