Opening Robotics, Language, and Vision
Robotics, Language, and Vision
- Length
- 1 h 25 min
- Level
- Undergraduate
- Recorded
- UC Berkeley2018
Chapter 1 of 11: Before the lecture
Infers a clean helicopter stunt trajectory from noisy pilot demonstrations with HMMs and dynamic time warping.
Applications of artificial intelligence in robotics, games and driving close session 24 of UC Berkeley's CS 188, taught by Pieter Abbeel and Daniel Klein. AlphaGo comes first: policy and value networks combined with tree search, then AlphaGo Zero learning Go without human knowledge. Autonomous helicopter flight follows, with hidden Markov models for state estimation and iterative LQR for control. Dynamic time warping aligns several noisy human demonstrations into one target trajectory for aggressive maneuvers. Legged robots crossing rocks, planned with learned reward functions and A* search, precede self-driving cars, self-supervised road detection and disengagement rates compared with human accident statistics.
Applications of artificial intelligence in robotics, games and driving close session 24 of UC Berkeley's CS 188, taught by Pieter Abbeel and Daniel Klein. AlphaGo comes first: policy and value networks combined with tree search, then AlphaGo Zero learning Go without human knowledge. Autonomous helicopter flight follows, with hidden Markov models for state estimation and iterative LQR for control. Dynamic time warping aligns several noisy human demonstrations into one target trajectory for aggressive maneuvers. Legged robots crossing rocks, planned with learned reward functions and A* search, precede self-driving cars, self-supervised road detection and disengagement rates compared with human accident statistics.
Mastering the game of Go with deep neural networks and tree search
Mastering the game of Go without human knowledge
Needleman & Wunsch 1970
Sakoe & Chiba, 1978

This lecture
Lecture 24 of 25 of Introduction to Artificial Intelligence.
Choose a node to see how it connects to this lecture. What comes before is on the leftat the top. What comes after is on the rightat the bottom. The ring is what it teaches. People and places are above.
Press a chosen node again to open it.
Your comment is kept while you sign up.Sign in