Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks

• URL: http://arxiv.org/abs/2207.03952v1
• Date: Fri, 8 Jul 2022 15:16:38 GMT
• Title: Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks
• Authors: Isabell Wochner, Pierre Schumacher, Georg Martius, Dieter B\"uchler, Syn Schmitt, Daniel F.B. Haeufle
• Abstract summary: Humans are able to outperform robots in terms of robustness, versatility, and learning of new tasks in a wide variety of movements. We hypothesize that highly nonlinear muscle dynamics play a large role in providing inherent stability, which is favorable to learning.
• Score: 13.545245521356218
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Humans are able to outperform robots in terms of robustness, versatility, and learning of new tasks in a wide variety of movements. We hypothesize that highly nonlinear muscle dynamics play a large role in providing inherent stability, which is favorable to learning. While recent advances have been made in applying modern learning techniques to muscle-actuated systems both in simulation as well as in robotics, so far, no detailed analysis has been performed to show the benefits of muscles in this setting. Our study closes this gap by investigating core robotics challenges and comparing the performance of different actuator morphologies in terms of data-efficiency, hyperparameter sensitivity, and robustness.

Related papers

• DiffuseBot: Breeding Soft Robots With Physics-Augmented Generative Diffusion Models [102.13968267347553]
  We present DiffuseBot, a physics-augmented diffusion model that generates soft robot morphologies capable of excelling in a wide spectrum of tasks. We showcase a range of simulated and fabricated robots along with their capabilities.
  arXiv  Detail & Related papers  (2023-11-28T18:58:48Z)
• The bionic neural network for external simulation of human locomotor system [2.6311880922890842]
  This paper proposes a physics-informed deep learning method based on musculoskeletal (MSK) modeling to predict joint motion and muscle forces. The method can effectively identify subject-specific MSK physiological parameters and the trained physics-informed forward-dynamics surrogate yields accurate motion and muscle forces predictions.
  arXiv  Detail & Related papers  (2023-09-11T23:02:56Z)
• Learning Human-to-Robot Handovers from Point Clouds [63.18127198174958]
  We propose the first framework to learn control policies for vision-based human-to-robot handovers. We show significant performance gains over baselines on a simulation benchmark, sim-to-sim transfer and sim-to-real transfer.
  arXiv  Detail & Related papers  (2023-03-30T17:58:36Z)
• Hindsight States: Blending Sim and Real Task Elements for Efficient Reinforcement Learning [61.3506230781327]
  In robotics, one approach to generate training data builds on simulations based on dynamics models derived from first principles. Here, we leverage the imbalance in complexity of the dynamics to learn more sample-efficiently. We validate our method on several challenging simulated tasks and demonstrate that it improves learning both alone and when combined with an existing hindsight algorithm.
  arXiv  Detail & Related papers  (2023-03-03T21:55:04Z)
• Morphological Wobbling Can Help Robots Learn [5.000272778136268]
  We consider quantities such as mass, actuator strength, and size that are usually fixed in a robot. We show that when those quantities oscillate at the beginning of the learning process on a simulated 2D soft robot, the performance on a task can be significantly improved.
  arXiv  Detail & Related papers  (2022-05-05T17:41:58Z)
• Revisiting the Adversarial Robustness-Accuracy Tradeoff in Robot Learning [121.9708998627352]
  Recent work has shown that, in practical robot learning applications, the effects of adversarial training do not pose a fair trade-off. This work revisits the robustness-accuracy trade-off in robot learning by analyzing if recent advances in robust training methods and theory can make adversarial training suitable for real-world robot applications.
  arXiv  Detail & Related papers  (2022-04-15T08:12:15Z)
• OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotion [8.849771760994273]
  We release a 3D musculoskeletal simulation of an ostrich based on the MuJoCo simulator. The model is based on CT scans and dissections used to gather actual muscle data. We also provide a set of reinforcement learning tasks, including reference motion tracking and a reaching task with the neck.
  arXiv  Detail & Related papers  (2021-12-11T19:58:11Z)
• What Matters in Learning from Offline Human Demonstrations for Robot Manipulation [64.43440450794495]
  We conduct an extensive study of six offline learning algorithms for robot manipulation. Our study analyzes the most critical challenges when learning from offline human data. We highlight opportunities for learning from human datasets.
  arXiv  Detail & Related papers  (2021-08-06T20:48:30Z)
• Modelling Human Kinetics and Kinematics during Walking using Reinforcement Learning [0.0]
  We develop an automated method to generate 3D human walking motion in simulation which is comparable to real-world human motion. We show that the method generalizes well across human-subjects with different kinematic structure and gait-characteristics.
  arXiv  Detail & Related papers  (2021-03-15T04:01:20Z)
• Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects [63.89096733478149]
  We introduce a data-driven approach where effective hand designs naturally emerge for the purpose of grasping diverse objects. We develop a novel Bayesian Optimization algorithm that efficiently co-designs the morphology and grasping skills jointly. We demonstrate the effectiveness of our approach in discovering robust and cost-efficient hand morphologies for grasping novel objects.
  arXiv  Detail & Related papers  (2020-12-22T17:52:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.