Boston Dynamics’ Spot now serves as a tour guide during the off season, while CMU’s Agile robot dog spends its time learning how to avoid obstacles at high-speed. This robot is powered by Agile But Safe (ABS), a learning-based control framework that enables agile and collision-free locomotion for quadrupedal robots.
Put simply, ABS utilizes an agile policy to execute agile motor skills amidst obstacles, while a a recovery policy prevents failures. When these two are combined, Agile is capable of achieving high-speed and collision-free navigation. Training the robot involves learning of the agile policy, the reach-avoid value network, the recovery policy, and an exteroception representation network, all in simulation.
No products found.
These trained modules can be directly deployed in the real world with onboard sensing and computation, leading to high-speed and collision-free navigation in confined indoor and outdoor spaces with both static and dynamic obstacles,” said the researchers.
[Source]
