Look at the images above. If I asked you to bring me a picnic blanket in the grassy field, would you be able to? If I asked you to bring over a cart full of food for a party, would you push the cart along the paved path or on the grass? Prior navigation approaches based purely on geometric reasoning incorrectly think that tall grass is an obstacle (above) and don't understand the difference between a smooth paved path and bumpy grass (below). While the answers to these questions may seem obvious, today's mobile robots would likely fail at these tasks: they would think the tall grass is the same as a concrete wall, and wouldn't know the difference between a smooth path and bumpy grass.

A new robot learning system that can learn about physical attributes of the environment through its own experiences in the real world, without the need for simulations or human supervision. University of California, Berkeley (UC Berkeley) researchers have developed a robot learning system that can learn about physical attributes of the environment through its own experiences in the real world, without the need for simulations or human supervision. BADGR: the Berkeley Autonomous Driving Ground Robot autonomously collects data and automatically labels it. The system uses that data to train an image-based neural network predictive model, and applies that model to plan and execute actions that will lead the robot to accomplish a desired navigational task. UC Berkeley's Gregory Kahn wrote, "The key insight behind BADGR is that by autonomously learning from experience directly in the real world, BADGR can learn about navigational affordances, improve as it gathers more data, and generalize to unseen environments."

Look at the images above. If I asked you to bring me a picnic blanket in the grassy field, would you be able to? If I asked you to bring over a cart full of food for a party, would you push the cart along the paved path or on the grass? Prior navigation approaches based purely on geometric reasoning incorrectly think that tall grass is an obstacle (left) and don't understand the difference between a smooth paved path and bumpy grass (right). While the answers to these questions may seem obvious, today's mobile robots would likely fail at these tasks: they would think the tall grass is the same as a concrete wall, and wouldn't know the difference between a smooth path and bumpy grass.

Mobile robot navigation is typically regarded as a geometric problem, in which the robot's objective is to perceive the geometry of the environment in order to plan collision-free paths towards a desired goal. However, a purely geometric view of the world can can be insufficient for many navigation problems. For example, a robot navigating based on geometry may avoid a field of tall grass because it believes it is untraversable, and will therefore fail to reach its desired goal. In this work, we investigate how to move beyond these purely geometric-based approaches using a method that learns about physical navigational affordances from experience. Our approach, which we call BADGR, is an end-to-end learning-based mobile robot navigation system that can be trained with self-supervised off-policy data gathered in real-world environments, without any simulation or human supervision. BADGR can navigate in real-world urban and off-road environments with geometrically distracting obstacles. It can also incorporate terrain preferences, generalize to novel environments, and continue to improve autonomously by gathering more data. Videos, code, and other supplemental material are available on our website https://sites.google.com/view/badgr