Dynamic terrain traversal skills using reinforcement learning
By Xue Bin Peng, Glen Berseth, Michiel van de Panne. 2015
75 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Control and Systems Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Sergey Levine
- Xue Bin Peng
- Pieter Abbeel
- Michiel van de Panne
- Chelsea Finn
- Glen Berseth
- Ruslan Salakhutdinov
- Jitendra Malik
In Computer Vision and Pattern Recognition
- Sergey Levine
- Pieter Abbeel
- Jitendra Malik
- Luc Van Gool
- Vladlen Koltun
- Dacheng Tao
- Trevor Darrell
- Ming-Hsuan Yang
In Control and Systems Engineering
- Sergey Levine
- Pieter Abbeel
- Xue Bin Peng
- Michiel van de Panne
- Chelsea Finn
- Jitendra Malik
- Glen Berseth
- Vikash Kumar
Citations in the corpus
- Sim-to-Real: Learning Agile Locomotion For Quadruped Robots (2018, neutral): “[32] developed a CACLA-inspired algorithm to control a simulated dog to navigate complex 1D terrains.”
- Exposure (2017, methodology): “In graphics, RL has been successfully used for character animation (Peng et al. 2015, 2016, 2017; Peng and van de Panne 2017).”
- DeepLoco (2017, background): “Learning of high-level controllers for physics-based characters has been successfully demonstrated for several locomotion and obstacle-avoidance tasks [Coros et al. 2009; Peng et al. 2015, 2016].”
- DeepMimic (2018, methodology): “Similar approaches have been explored for simulated characters [Coros et al. 2009; Peng et al. 2015].”
- Terrain-adaptive locomotion skills using deep reinforcement learning (2016, methodology): “2011], τg provides gravity compensation for all links, as referred back to the root link, and τvf implements virtual leg forces for the front and hind legs when they are in contact with the ground, as described in detail in [Peng et al. 2015].”