Roboticists Go Off Road To Compile Data That Could Train Self-Driving ATVs

June 30, 2022

But that sort of information isn’t often available and, even when it is, might not be useful. The research team found that the multimodal sensor data they gathered for TartanDrive enabled them to build prediction models superior to those developed with simpler, nondynamic data. Driving aggressively also pushed the ATV into a performance realm where an understanding of dynamics became essential, said Samuel Triest, a second-year master’s student in robotics. The team’s tests were performed at a site near Pittsburgh that CMU’s National Robotics Engineering Center uses to test autonomous off-road vehicles. “We were forcing the human to go through the same control interface as the robot would,” Wang said.

The source of this news is from Carnegie Mellon University, The Robotics Institute

Popular in Robot Platform


Nov 19, 2023

ANYmal Closes the Remote Inspection Loop with Aker BP and Cognite


Nov 22, 2023

Petrobras and ANYbotics Join Efforts to Automate Offshore FPSO Inspections


4 days ago

GM, Cruise and Honda Are Bringing Autonomous Vehicle Ridehail Service to Japan


3 days ago

A new optimization framework for robot motion planning


Nov 19, 2023

Changliu Liu Receives Advanced Robotics for Manufacturing Champion Award

New method uses crowdsourced feedback to help train robots

1 week ago

Dubrawski Receives Fulbright Specialist Award

Nov 19, 2023

Unveiling the Future of Automation Technology

Nov 19, 2023

Startup of the Year

Nov 5, 2023

How Process Automation Enables Sustainability

Jul 2, 2023

Automation Empowered: The Edge Computing Advantage

Jun 30, 2023

This 3D printer can watch itself fabricate objects

Nov 19, 2023

LEMUR 2 – New, Improved and Shipping Now

Nov 2, 2023