Hierarchical Motion Learning for Goal-Oriented Movements With Speed–Accuracy Tradeoff of a Musculoskeletal System

Zhou, Junjie; Zhong, Shanlin; Wu, Wenfeng

doi:10.1109/tcyb.2021.3109021

Cited by 10 publications

(8 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Biological structures and mechanisms such as the hierarchical structure of motor control, and autonomy and amortized control ability of sub-regions in Section 2.2.3 may give some inspiration. We hypothesize that hierarchical RL and curriculum learning are potential frameworks (Zhou et al, 2021 ). Cloud robotics with shared memory and meta learning are also very related topics.…”

Section: Discussion and Open Issuesmentioning

confidence: 99%

A Survey of Multifingered Robotic Manipulation: Biological Results, Structural Evolvements, and Learning Methods

Wang

et al. 2022

Front. Neurorobot.

View full text Add to dashboard Cite

Multifingered robotic hands (usually referred to as dexterous hands) are designed to achieve human-level or human-like manipulations for robots or as prostheses for the disabled. The research dates back 30 years ago, yet, there remain great challenges to effectively design and control them due to their high dimensionality of configuration, frequently switched interaction modes, and various task generalization requirements. This article aims to give a brief overview of multifingered robotic manipulation from three aspects: a) the biological results, b) the structural evolvements, and c) the learning methods, and discuss potential future directions. First, we investigate the structure and principle of hand-centered visual sensing, tactile sensing, and motor control and related behavioral results. Then, we review several typical multifingered dexterous hands from task scenarios, actuation mechanisms, and in-hand sensors points. Third, we report the recent progress of various learning-based multifingered manipulation methods, including but not limited to reinforcement learning, imitation learning, and other sub-class methods. The article concludes with open issues and our thoughts on future directions.

show abstract

Section: Discussion and Open Issuesmentioning

confidence: 99%

A Survey of Multifingered Robotic Manipulation: Biological Results, Structural Evolvements, and Learning Methods

Wang

et al. 2022

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

“…Depending on whether explicit models of musculoskeletal robots are established during the solution process, these methods can be divided into two categories: modelbased and model-free methods as shown in Table 3. The details are as follows: Model-free methods [87][88][89][90][91][92][93][94] Brain-inspired methods Muscle-synergies-inspired methods [95,96] Cortex-inspired methods [97,98] Hierarchical-mechanisminspired methods [99,100] Cerebellum-inspired methods [101,102] Many model-based control methods for musculoskelet-al robots have been proposed by establishing kinematic and dynamic models of musculoskeletal systems. First, static and dynamic optimizations were used to study musculoskeletal robots.…”

Section: Brain-inspired Motion Control 231 Methods Based On Control T...mentioning

confidence: 99%

“…With the modulation of the initial states, the initial learned states can be explicitly expressed as the knowledge of movements and can be utilized to construct a proper initial state corresponding to a new movement target, significantly improving the generalization efficiency for new movements. To accelerate solution space exploration and reduce the difficulty of learning, considering that the learning goal of humans changes stepwise with the progress of learning, Zhou et al [99] proposed a phased target learning framework with hierarchical task architecture that provides different targets to learners at varying levels. This realized a tracking task based on the musculoskeletal arm.…”

Section: Brain-inspired Control Methodsmentioning

confidence: 99%

Brain-inspired Intelligent Robotics: Theoretical Analysis and Systematic Application

Qiao

Zhong

et al. 2023

Mach. Intell. Res.

View full text Add to dashboard Cite

Traditional joint-link robots have been widely used in production lines because of their high precision for single tasks. With the development of the manufacturing and service industries, the requirement for the comprehensive performance of robotics is growing. Numerous types of bio-inspired robotics have been investigated to realize human-like motion control and manipulation. A study route from inner mechanisms to external structures is proposed to imitate humans and animals better. With this idea, a brain-inspired intelligent robotic system is constructed that contains visual cognition, decision-making, motion control, and musculoskeletal structures. This paper reviews cutting-edge research in brain-inspired visual cognition, decision-making, motion control, and musculoskeletal systems. Two software systems and a corresponding hardware system are established, aiming at the verification and applications of next-generation brain-inspired musculoskeletal robots.

show abstract

“…A human arm contains several antagonistic muscles and a complicated series–parallel mixed skeletal joint structure, while a single muscle comprises many skeletal anchors (Holzbaur et al , 2005). The human arm can rapidly, flexibly, safely and robustly complete complex operation tasks with high robustness, muscle nonlinearity and multimuscle redundancy (Qiao et al , 2021; Chen and Qiao, 2021; Zhong et al , 2021; Zhou et al , 2022; Qiao et al , 2022). Arm-musculoskeletal robots have been extensively studied owing to the flexibility of their skeletal joints (such as the absence of singular positions of shoulder-ball joints) and the variable stiffness control due to from multiple antagonistic muscles (Kawaharazuka et al , 2019; Asano et al , 2017; Kozuki et al , 2012; Wittmeier et al , 2013; Zhong et al , 2022).…”

Section: Introductionmentioning

confidence: 99%

Design and input saturation control with full-state constraints of lightweight tendon-driven musculoskeletal arm

Yuan

Fan

2023

RIA

View full text Add to dashboard Cite

Purpose This study aims to propose a novel lightweight tendon-driven musculoskeletal arm (LTDM-arm) robot with a flexible series–parallel mixed skeletal joint structure and modularized artificial muscle system (MAMS). The proposed LTDM-arm exhibits human-like flexibility, safety and operational accuracy. In addition, to improve the safety and stability of the LTDM-arm, a control method is proposed to solve local artificial muscle overload accidents. Design/methodology/approach The proposed LTDM-arm comprises seven degrees of freedom skeletons, 15 MAMSs and various sensor systems (joint sensing, muscle tension sensing, visual sensing, etc.). It retains the morphology of a human skeleton (humerus, ulna and radius) and a simplified muscle configuration. This study proposes an input saturation control with full-state constraints to reduce local artificial muscle overload accidents caused by redundant muscle tension calculations. Findings 3D circular trajectory experiments were conducted to verify the stability of the control method and the flexibility of the LTDM-arm. The results showed that the average error of the muscle length was approximately 0.35 mm (0.38%), which indicates that the proposed control scheme can make the output follow the target trajectory while ensuring constraint satisfaction. Originality/value The human arm is capable of performing compliant operations rapidly, flexibly and robustly in unstructured environments. Existing musculoskeletal arm robots lack simulations of the full morphology of the human arm and are insufficient in dexterity. However, the flexibility and safety features of the proposed LTDM-arm were consistent with that of the human arm. Therefore, this study offers a new approach for investigating the advantages of the musculoskeletal system and the concepts of muscle control.

show abstract

Hierarchical Motion Learning for Goal-Oriented Movements With Speed–Accuracy Tradeoff of a Musculoskeletal System

Cited by 10 publications

References 60 publications

A Survey of Multifingered Robotic Manipulation: Biological Results, Structural Evolvements, and Learning Methods

A Survey of Multifingered Robotic Manipulation: Biological Results, Structural Evolvements, and Learning Methods

Brain-inspired Intelligent Robotics: Theoretical Analysis and Systematic Application

Design and input saturation control with full-state constraints of lightweight tendon-driven musculoskeletal arm

Contact Info

Product

Resources

About