Learning Legged Locomotion by Physics-based Initialization: Motion Imitation from Model-Based Optimal Control
The development of legged robots capable of navigating in and interacting with the world is quickly advancing as new methods and techniques for sensing, decisionmaking, and controls expand the capabilities of state-of-the-art systems. Model-based methods, empowered by greater computing capacity and...
Váldodahkki: | Miller, Adam Joseph |
---|---|
Eará dahkkit: | Kim, Sangbae |
Materiálatiipa: | Oahppočájánas |
Almmustuhtton: |
Massachusetts Institute of Technology
2023
|
Liŋkkat: | https://hdl.handle.net/1721.1/147283 |
Geahča maid
-
Structuring Optimal Control of Legged Locomotion with Learning-based Methods
Dahkki: Jeon, Se Hwan
Almmustuhtton: (2022) -
Receding-horizon perceptive trajectory optimization for dynamic legged locomotion with learned initialization
Dahkki: Melon, O, et al.
Almmustuhtton: (2021) -
Leg swinging motion modeling of a legged locomotion of walking and climbing robot /
Dahkki: 288997 Shamsudin Mohd. Amin, et al. -
Applied optimal control for dynamically stable legged locomotion
Dahkki: Tedrake, Russell L., 1977-
Almmustuhtton: (2005) -
RLOC: terrain-aware legged locomotion using reinforcement learning and optimal control
Dahkki: Gangapurwala, S, et al.
Almmustuhtton: (2022)