What is the current way robots can assess and traverse difficult obstacles in 3d space?

I could see manual feature extraction using stereo vision (for example, the height of the obstacle, "smoothness", etc.), but I am wondering if Deep RL can work?

Or even something involving model-based planning, where you internally run an RRT algorithm on the obstacle in real-time using a physics engine (but it's not clear to me how well a physics engine could actually model the environment).


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.