Learning symmetric and low-energy locomotion
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Learning locomotion skills is a challenging problem. To generate realistic and smooth locomotion, existing methods use motion capture, finite state machines or morphology-specific knowledge to guide the motion generation algorithms. Deep reinforcement learning (DRL) is a promising approach for the automatic creation of locomotion control. Indeed, a standard benchmark for DRL is to automatically create a running controller for a biped character from a simple reward function [Duan et al. 2016]. Although several different DRL algorithms can successfully create a running controller, the resulting motions usually look nothing like a real runner. This paper takes a minimalist learning approach to the locomotion problem, without the use of motion examples, finite state machines, or morphology-specific knowledge. We introduce two modifications to the DRL approach that, when used together, produce locomotion behaviors that are symmetric, low-energy, and much closer to that of a real person. First, we introduce a new term to the loss function (not the reward function) that encourages symmetric actions. Second, we introduce a new curriculum learning method that provides modulated physical assistance to help the character with left/right balance and forward movement. The algorithm automatically computes appropriate assistance to the character and gradually relaxes this assistance, so that eventually the character learns to move entirely without help. Because our method does not make use of motion capture data, it can be applied to a variety of character morphologies. We demonstrate locomotion controllers for the lower half of a biped, a full humanoid, a quadruped, and a hexapod. Our results show that learned policies are able to produce symmetric, low-energy gaits. In addition, speed-appropriate gait patterns emerge without any guidance from motion examples or contact planning.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Continuous control with deep reinforcement learning
Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015) · arXiv · doi:10.48550/arxiv.1509.02971 · Cited by 10,782
Proximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625 · cited 14×
“Later, they proposed Proximal Policy Optimization (PPO), which further improved the data efficiency of the algorithm [Schulman et al. 2017].”
BackgroundMethodInfluentialAsynchronous Methods for Deep Reinforcement Learning
Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T. P., Harley, T., Silver, D., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1602.01783 · Cited by 7,132 · cited 2×
“…significant progress on improving the gradient estimation accuracy and stability of training, leading to algorithms such as DDPG [Lillicrap et al. 2015], A3C [Mnih et al. 2016], TRPO [Schulman et al. 2015a], and PPO [Schulman et al. 2017], which can be used to solve complex motor control problems.”
BackgroundMethodBengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 3×
“…in machine learning have shown that CL can improve performance and efficiency of learning problems such as question-answering [Graves et al. 2017], classification [Bengio et al. 2009; Pentina et al. 2015], navigation [Held et al. 2017; Matiisen et al. 2017] and game playing [Narvekar et al. 2016].”
BackgroundBenchmarking Deep Reinforcement Learning for Continuous Control
Duan, Y., Chen, X., Houthooft, R., Schulman, J., & Abbeel, P. (2016) · arXiv · doi:10.48550/arxiv.1604.06778 · Cited by 1,114
Emergence of Locomotion Behaviours in Rich Environments
Heess, N., TB, D., Sriram, S., Lemmon, J., Merel, J., Wayne, G., Tassa, Y., Erez, T., Wang, Z., Eslami, S. M. A., et al. (2017) · arXiv · doi:10.48550/arxiv.1707.02286 · Cited by 657 · cited 2×
“More recently, Heess et al. demonstrated learning of agile locomotion controllers in a complex environment using deep Reinforcement Learning [Heess et al. 2017].”
Methodpeng (2017) · doi:10.1145/3072959.3073602 · Cited by 502
Optimizing walking controllers
Wang, J. M., Fleet, D. J., & Hertzmann, A. (2009) · ACM Transactions on Graphics · doi:10.1145/1618452.1618514 · Cited by 181
Learning to schedule control fragments for physics-based characters using deep q-learning
Liu, L., & Hodgins, J. (2017) · ACM Transactions on Graphics · doi:10.1145/3083723 · Cited by 49
Cited by
Learning agile and dynamic motor skills for legged robots
Hwangbo, J., Lee, J., Dosovitskiy, A., Bellicoso, D., Tsounis, V., Koltun, V., & Hutter, M. (2019) · Science Robotics · doi:10.1126/scirobotics.aau5872 · Cited by 1,482
Learning quadrupedal locomotion over challenging terrain
Lee, J., Hwangbo, J., Wellhausen, L., Koltun, V., & Hutter, M. (2020) · Science Robotics · doi:10.1126/scirobotics.abc5986 · Cited by 1,156
“Instead of directly using the reward function to evaluate the learning progress [25, 41–43], we evaluate cTs by the traversability of generated terrains, which is defined as the success rate of traversing a terrain.”
How to train your robot with deep reinforcement learning: Lessons we have learned
Ibarz, J., Tan, J., Finn, C., Kalakrishnan, M., Pastor, P., & Levine, S. (2021) · The International Journal of Robotics Research · doi:10.1177/0278364920987859 · Cited by 570
“In fact, most of the prior work used simulation (Brockman et al. 2016; Coumans and Bai 2016) to evaluate and benchmark the learning algorithms (H ¨ am ¨ al ¨ ainen et al. 2015; Heess et al. 2017; Yu et al. 2018; Peng et al. 2018a).”
MethodAMP: adversarial motion priors for stylized physics-based character control
Peng, X. B., Ma, Z., Abbeel, P., Levine, S., & Kanazawa, A. (2021) · ACM Transactions on Graphics · doi:10.1145/3450626.3459670 · Cited by 396
Embodied intelligence via learning and evolution
Gupta, A., Savarese, S., Ganguli, S., & Fei-Fei, L. (2021) · Nature Communications · doi:10.1038/s41467-021-25874-z · Cited by 352
“We measure energy as the absolute sum of all joint torques 55 .”
Method
Metadata
- Authors
- Yu, W., Turk, G., & Liu, C. K.
- Venue
- ACM Transactions on Graphics
- Published
- 2018-07-30
- Volume
- 37
- Issue
- 4
- Pages
- 1-12
- ISSN
- 0730-0301 (ISSN-L)
- 1557-7368
- OpenAlex
- W2784449021
- Cited by
- 155
- References
- 10
- FWCI
- 9.00
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.