We investigate a hierarchical approach to robot control inspired by joint-level control in animals. The method combines a high-level controller, consisting of an artificial neural network (ANN), with joint-level controllers based on digital muscles. In the digital muscle model (DMM), morphological and control aspects of joints evolve concurrently, emulating the musculoskeletal system of natural organisms. We introduce and compare different approaches for connecting outputs of the ANN to DMM-based joints. We also compare the performance of evolved animats with ANN-DMM controllers with those governed by only high-level (ANN-only) and low-level (DMM-only) controllers. These results show that DMM-based systems outperform their ANN-only counterparts while also exhibiting less complex ANNs in terms of the number of connections and neurons. The main contribution of this work is to explore the evolution of artificial systems where, as in natural organisms, some aspects of control are realized at the joint level.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1162/ARTL_a_00222 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Residual force enhancement is not altered while force depression is amplified at the cellular level in old age.
J Exp Biol
January 2025
Department of Human Health and Nutritional Sciences, College of Biological Sciences, University of Guelph, Guelph, ON, Canada, N1G 2W1.
Residual force enhancement (rFE) and residual force depression (rFD) are history-dependent properties of muscle which refer to increased and decreased isometric force following a lengthening or shortening contraction, respectively. The history dependence of force is greater in older than in younger human adults when assessed at the joint level. However, it is unclear whether this amplification of the history dependence of force in old age is owing to cellular mechanisms or is a consequence of age-related remodelling of muscle architecture.
View Article and Find Full Text PDFEvaluating the Effectiveness of Commercially Available Antiadhesion Tendon Protector Sheets in Tendon Repair Surgery Versus Tendon Repair Surgery Alone: A Preclinical Model Study.
J Hand Surg Am
September 2024
Department of Orthopedic Surgery, Mayo Clinic, Rochester, MN; Division of Plastic Surgery, Department of Surgery, Mayo Clinic, Rochester, MN. Electronic address:
Purpose: Adhesion formation is the major complication after tendon repairs that halts functional restoration and causes disability in patients. This study aimed to compare the antiadhesion efficacy of two tendon protector sheets using a previously established turkey flexor tendon model.
Methods: Twenty-four adult Bourbon Red turkeys were randomized into three groups: (1) control, (2) type I collagen-glycosaminoglycan (Collagen-GAG), and (3) hyaluronic acid.
Research on design and control methods of a lightweight upper limb joint isokinetic rehabilitation training equipment.
Front Bioeng Biotechnol
September 2024
Institute of Rehabilitation Engineering and Technology, University of Shanghai for Science and Technology, Shanghai, China.
Introduction: Isokinetic exercise can improve joint muscle strength and stability, making it suitable for early rehabilitation of stroke patients. However, traditional isokinetic equipment is bulky and costly, and cannot effectively avoid external environmental interference.
Methods: This paper designed a lightweight upper limb joint isokinetic rehabilitation training equipment, with a control system that includes a speed planning strategy and speed control with disturbance rejection.
The effect of motor experience on knee stability and inter-joint coordination when cutting at different angles.
Knee
June 2024
College of Physical Education and Sports, Beijing Normal University, Beijing, China. Electronic address:
Background: Most studies on cutting have focused on the biomechanics of the knee and lower-limb muscle activation characteristics, with less consideration given to the influence of motor experience on control strategies at the joint level. This study aimed to investigate the differences in knee stability and inter-joint coordination between high- and low-level athletes when cutting at different angles.
Methods: A Vicon motion capture system and a Kistler force table were used to obtain kinematic and ground reaction force data during cutting.
Swing-phase detection of locomotive mode transitions for smooth multi-functional robotic lower-limb prosthesis control.
Front Robot AI
April 2024
Human-Centered Bio-Robotics Lab, Department of Mechanical Engineering, The University of Alabama, Tuscaloosa, AL, United States.
Robotic lower-limb prostheses, with their actively powered joints, may significantly improve amputee users' mobility and enable them to obtain healthy-like gait in various modes of locomotion in daily life. However, timely recognition of the amputee users' locomotive mode and mode transition still remains a major challenge in robotic lower-limb prosthesis control. In the paper, the authors present a new multi-dimensional dynamic time warping (mDTW)-based intent recognizer to provide high-accuracy recognition of the locomotion mode/mode transition sufficiently early in the swing phase, such that the prosthesis' joint-level motion controller can operate in the correct locomotive mode and assist the user to complete the desired (and often power-demanding) motion in the stance phase.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!