WEBINAR
Next Frontiers in Robotic AI and Autonomy
A perspective from Team CoSTAR that won the DARPA Subterranean Challenge, Urban Circuit
The DARPA Subterranean or “SubT” Challenge is a robotic/software competition that seeks novel and revolutionary approaches to rapidly map, navigate, and search unknown and complex underground environments. The challenge spans a period of three years with several competitions and a final event developing next generation autonomy solutions for extreme environment exploration.
In this presentation we will go over TEAM-CoSTAR’s technologies that won the Phase 2 of this challenge, focused on autonomously and robotically exploring unknown and complex industrial facilities and urban underground. In particular, we will discuss CoSTAR’s autonomy and AI solution (called, NeBula) and its elements including:
1. Mobility and traversability
2. State estimation in perceptually-degraded environments
3. Large scale mapping and SLAM
4. Multi-robot autonomy
5. Communication
6. Learning-based semantic understanding.
Team website: https://costar.jpl.nasa.gov/
Next Frontiers in Robotic AI and Autonomy
A perspective from Team CoSTAR that won the DARPA Subterranean Challenge, Urban Circuit
The DARPA Subterranean or “SubT” Challenge is a robotic/software competition that seeks novel and revolutionary approaches to rapidly map, navigate, and search unknown and complex underground environments. The challenge spans a period of three years with several competitions and a final event developing next generation autonomy solutions for extreme environment exploration.
In this presentation we will go over TEAM-CoSTAR’s technologies that won the Phase 2 of this challenge, focused on autonomously and robotically exploring unknown and complex industrial facilities and urban underground. In particular, we will discuss CoSTAR’s autonomy and AI solution (called, NeBula) and its elements including:
1. Mobility and traversability
2. State estimation in perceptually-degraded environments
3. Large scale mapping and SLAM
4. Multi-robot autonomy
5. Inter-robot Communication
6. Learning-based semantic understanding.
Team website: https://costar.jpl.nasa.gov/
About the presenter
Dr. Ali-akbar Agha-mohammadi is a Robotics Research Technologist at NASA’s Jet Propulsion Laboratory (JPL), Caltech, where he is leading several projects focused on robotic autonomy with a dual focus on Mars exploration and terrestrial applications. Dr. Agha leads the team CoSTAR and the development of the NeBula autonomy architecture which won the DARPA Subterranean Challenge, Urban Circuit, in February 2020. Previously, he was with Qualcomm Research, leading the perception efforts for self-flying drones and autonomous cars. Prior to that, Dr. Agha was a Postdoctoral Researcher at MIT. His research interests include AI, autonomous decision making, and perception for robotic systems, with applications to drones, rovers, and legged robots. Dr. Agha selected as a NASA NIAC fellow in 2018.