Видео

Presented at ICRA 2024 Authors: Arun Bishop, John Zhang, Swaminathan Gurumurthy, Kevin Tracy, and Zac Manchester Paper: arxiv.org/abs/2311.18056

Lecture 23 for Optimal Control and Reinforcement Learning 2024 by Prof. Zac Manchester. Topics: - Calculus of Variations - Physics as Trajectory Optimization - Hamilton, Pontryagin, and Lagrange - Contact Dynamics

Lecture 22 for Optimal Control and Reinforcement Learning 2024 by Prof. Zac Manchester. Topics: - MPC for autonomous driving - The "freezing robot problem" - Dynamic games and Nash equilibria

Lecture 20 for Optimal Control and Reinforcement Learning 2024 by Prof. Zac Manchester. Topics: - Rocket Soft-Landing Problem - Convex Relaxation

Lecture 21 for Optimal Control and Reinforcement Learning 2024 by Prof. Zac Manchester. Topics: - History of legged robots - Centroidal dynamics - QP-based MPC for quadrupeds

Lecture 19 for Optimal Control and Reinforcement Learning 2024 by Prof. Zac Manchester. Topics: - Kalman Filters - LQG example - Duality between control and state estimation

Lecture 18 for Optimal Control and Reinforcement Learning 2024 by Prof. Zac Manchester. Topics: - Stochastic Optimal Control Intro - The LQG Problem - The Separation Principle and Certainty Equivalence

Lecture 17 for Optimal Control and Reinforcement Learning 2024 by Prof. Zac Manchester. Topics: - Convex vs. non-convex optimization review - Iterative Learning Control (ILC)

Lecture 14 for Optimal Control and Reinforcement Learning 2024 by Prof. Zac Manchester. Topics: - Quaternion recap - Differentiating with respect to quaternion variables - Optimization with quaternion variables

Lecture 13 for Optimal Control and Reinforcement Learning 2024 by Prof. Zac Manchester. Topics: - Recap: Algorithms for deterministic optimal control problems - Introduction to 3D rotations, attitude, and quaternions

Lecture 12 for Optimal Control and Reinforcement Learning (CMU 16-745) 2024 by Prof. Zac Manchester. Topics: - Free and minimum-time problems - Direct trajectory optimization - Sequential quadratic programming (SQP) - Direct collocation

Lecture 11 for Optimal Control and Reinforcement Learning (CMU 16-745) 2024 by Prof. Zac Manchester. Topics: - DDP details extensions - Constraints

Lecture 10 for Optimal Control and Reinforcement Learning (CMU 16-745) 2024 by Prof. Zac Manchester. Topics: - Convex MPC applications - Nonlinear Trajectory Optimization Problem - Matrix calculus tricks - Differential Dynamic Programming

Lecture 9 for Optimal Control and Reinforcement Learning (CMU 16-745) 2024 by Prof. Zac Manchester. Topics: - Convexity Background - Convex Model-Predictive Control

Optimal Control (CMU 16-745) 2024 Lecture 8: Controllability and Dynamic Programming

Optimal Control (CMU 16-745) 2024 Lecture 7: The Linear Quadratic Regulator Three Ways

Optimal Control (CMU 16-745) 2024 Lecture 6: Deterministic Optimal Control Intro

Optimal Control (CMU 16-745) 2024 Lecture 5: Optimization Pt. 3

Optimal Control (CMU 16-745) 2024 Lecture 4: Optimization Pt. 2

Optimal Control (CMU 16-745) 2024 Lecture 3: Optimization Pt. 1

Optimal Control (CMU 16-745) 2024 Lecture 2: Dynamics Discretization and Stability

Optimal Control (CMU 16-745) 2024 Lecture 1: Intro and Dynamics Review

TinyMPC: Model-Predictive Control on Resource-Constrained Microcontrollers

Kilometer-Scale Deployable Space Structures - 2023 NIAC Symposium

Optimal Control (CMU 16-745) 2023 Lecture 22: Legged Robots and How to Walk with QPs

Optimal Control (CMU 16-745) 2023 Lecture 24: Reinforcement Learning

Optimal Control (CMU 16-745) 2023 Lecture 23: Autonomous Driving and Game Theory

Optimal Control (CMU 16-745) 2023 Lecture 21: Convex Relaxation and Landing Rockets

Optimal Control (CMU 16-745) 2023 Lecture 20: Robust Control and Minimax Optimization