Earth Rover
applications encouraged
Prize: up to $1m
Challenge active
apply now
Challenge overview
mission details
summary
Human gamer teams compete with AI teams in an ongoing urban navigation challenge to advance Embodied AI. In this challenge, gamers and AIs will compete in two phases navigating “in-the-wild” GPS goal-oriented scenarios.
In the first phase, competitors will navigate in a seen environment driving across the Bay Area (from UC Berkeley campus to Stanford University campus). This will be repeated regularly until a winning AI model is finally able to beat human benchmarks on the same task.
In the second phase, similar navigation challenges will be conducted except that this will be done in unseen environments in various cities around the world.
Co-organizers
Researchers from Google DeepMind and academia (NUS, NYU, GMU, Princeton, etc.), FrodoBots Lab
prize
Up to $1m
Up to $1M USD in prizes will be awarded to teams that demonstrate measurable breakthroughs in autonomous navigation, evaluated against a defined set of goals and benchmarks.
entry requirements
All considered
Teams and researchers of all levels are encouraged to participate in the Challenge, from hobbyist roboticists to research organizations. Prizes are awarded on merit and results, not team pedigree.
Engage with the Challenge
opportunities available
get in contact
Other open challenges
Robotic Origami
Human origami experts compete with AI teams in an ongoing robotic origami challenge to advance robotic hand dexterity.
Prize
Up to $1M
Application date
Open Now
Partners
BitRobot, FrodoBots Lab, Agility Robotics, Nippon Origami Association (日本折紙協会), Sharpa Hands, Lightwheel, Toyota Central R&D Labs. NUS, Stanford University, Tsinghua University
Robotic IKEA Furniture Assembly
Human origami experts compete with AI teams in an ongoing robotic origami challenge to advance robotic hand dexterity.
Prize
Up to $1M
Application date
Open Now
Partners
Researchers from BitRobot, Unitree, Lightwheel, and Singapore Institue of Technology
