RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewards

• URL: http://arxiv.org/abs/2407.11562v1
• Date: Tue, 16 Jul 2024 10:15:35 GMT
• Title: RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewards
• Authors: Fatemeh Zargarbashi, Jin Cheng, Dongho Kang, Robert Sumner, Stelian Coros,
• Abstract summary: This paper presents a novel learning-based control framework for legged robots. It incorporates high-level objectives in natural locomotion for legged robots. It uses a multi-critic reinforcement learning algorithm to handle the mixture of dense and sparse rewards.
• Score: 15.79235618199162
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper presents a novel learning-based control framework that uses keyframing to incorporate high-level objectives in natural locomotion for legged robots. These high-level objectives are specified as a variable number of partial or complete pose targets that are spaced arbitrarily in time. Our proposed framework utilizes a multi-critic reinforcement learning algorithm to effectively handle the mixture of dense and sparse rewards. Additionally, it employs a transformer-based encoder to accommodate a variable number of input targets, each associated with specific time-to-arrivals. Throughout simulation and hardware experiments, we demonstrate that our framework can effectively satisfy the target keyframe sequence at the required times. In the experiments, the multi-critic method significantly reduces the effort of hyperparameter tuning compared to the standard single-critic alternative. Moreover, the proposed transformer-based architecture enables robots to anticipate future goals, which results in quantitative improvements in their ability to reach their targets.

Related papers

• AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer [54.713778961605115]
  Vision Transformer (ViT) has become one of the most prevailing fundamental backbone networks in the computer vision community. We propose a novel non-uniform quantizer, dubbed the Adaptive Logarithm AdaLog (AdaLog) quantizer.
  arXiv  Detail & Related papers  (2024-07-17T18:38:48Z)
• Enhancing Robotic Navigation: An Evaluation of Single and Multi-Objective Reinforcement Learning Strategies [0.9208007322096532]
  This study presents a comparative analysis between single-objective and multi-objective reinforcement learning methods for training a robot to navigate effectively to an end goal. By modifying the reward function to return a vector of rewards, each pertaining to a distinct objective, the robot learns a policy that effectively balances the different goals.
  arXiv  Detail & Related papers  (2023-12-13T08:00:26Z)
• Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning [99.38163119531745]
  We show that applying a discretizing bottleneck can improve performance in goal-conditioned RL setups. We experimentally prove the expected return on out-of-distribution goals, while still allowing for specifying goals with expressive structure.
  arXiv  Detail & Related papers  (2022-11-01T03:31:43Z)
• Meta-Learning with Self-Improving Momentum Target [72.98879709228981]
  We propose Self-improving Momentum Target (SiMT) to improve the performance of a meta-learner. SiMT generates the target model by adapting from the temporal ensemble of the meta-learner. We show that SiMT brings a significant performance gain when combined with a wide range of meta-learning methods.
  arXiv  Detail & Related papers  (2022-10-11T06:45:15Z)
• Efficient and Robust Training of Dense Object Nets for Multi-Object Robot Manipulation [8.321536457963655]
  We propose a framework for robust and efficient training of Dense Object Nets (DON) We focus on training with multi-object data instead of singulated objects, combined with a well-chosen augmentation scheme. We demonstrate the robustness and accuracy of our proposed framework on a real-world robotic grasping task.
  arXiv  Detail & Related papers  (2022-06-24T08:24:42Z)
• Graph-based Reinforcement Learning meets Mixed Integer Programs: An application to 3D robot assembly discovery [34.25379651790627]
  We tackle the problem of building arbitrary, predefined target structures entirely from scratch using a set of Tetris-like building blocks and a robotic manipulator. Our novel hierarchical approach aims at efficiently decomposing the overall task into three feasible levels that benefit mutually from each other.
  arXiv  Detail & Related papers  (2022-03-08T14:44:51Z)
• Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms [60.59764170868101]
  Reinforcement learning methods can achieve significant performance but require a large amount of training data collected on the same robotic platform. We formulate it as a few-shot meta-learning problem where the goal is to find a model that captures the common structure shared across different robotic platforms. We experimentally evaluate our framework on a simulated reaching and a real-robot picking task using 400 simulated robots.
  arXiv  Detail & Related papers  (2021-03-05T14:16:20Z)
• Deep Imitation Learning for Bimanual Robotic Manipulation [70.56142804957187]
  We present a deep imitation learning framework for robotic bimanual manipulation. A core challenge is to generalize the manipulation skills to objects in different locations. We propose to (i) decompose the multi-modal dynamics into elemental movement primitives, (ii) parameterize each primitive using a recurrent graph neural network to capture interactions, and (iii) integrate a high-level planner that composes primitives sequentially and a low-level controller to combine primitive dynamics and inverse kinematics control.
  arXiv  Detail & Related papers  (2020-10-11T01:40:03Z)
• Integrated Benchmarking and Design for Reproducible and Accessible Evaluation of Robotic Agents [61.36681529571202]
  We describe a new concept for reproducible robotics research that integrates development and benchmarking. One of the central components of this setup is the Duckietown Autolab, a standardized setup that is itself relatively low-cost and reproducible. We validate the system by analyzing the repeatability of experiments conducted using the infrastructure and show that there is low variance across different robot hardware and across different remote labs.
  arXiv  Detail & Related papers  (2020-09-09T15:31:29Z)
• Learning from Sparse Demonstrations [17.24236148404065]
  The paper develops the method of Continuous Pontryagin Differentiable Programming (Continuous PDP), which enables a robot learn an objective function from a few demonstrated examples. The method finds an objective function and a time-warping function such that the robot's resulting trajectorys sequentially follow the trajectorys with minimal discrepancy loss. The method is first evaluated on a simulated robot arm and then applied to a 6-DoF quadrotor to learn an objective function for motion planning in unmodeled environments.
  arXiv  Detail & Related papers  (2020-08-05T14:25:39Z)
• Real-Time Object Detection and Recognition on Low-Compute Humanoid Robots using Deep Learning [0.12599533416395764]
  We describe a novel architecture that enables multiple low-compute NAO robots to perform real-time detection, recognition and localization of objects in its camera view. The proposed algorithm for object detection and localization is an empirical modification of YOLOv3, based on indoor experiments in multiple scenarios. The architecture also comprises of an effective end-to-end pipeline to feed the real-time frames from the camera feed to the neural net and use its results for guiding the robot.
  arXiv  Detail & Related papers  (2020-01-20T05:24:58Z)

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.