1
|
Long S, Dang X, Huang J. FOESO-Net: A specific neural network for fast sensorless robot manipulator torque estimation. Neural Netw 2023; 168:14-31. [PMID: 37734136 DOI: 10.1016/j.neunet.2023.09.020] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2023] [Revised: 07/19/2023] [Accepted: 09/10/2023] [Indexed: 09/23/2023]
Abstract
Contact torque sensing allows robot manipulators to cooperate with humans and detect accidental collisions in real time to ensure safety. Most sensorless torque estimation schemes, which are based on linear observer approaches, cannot compromise between non-negligible noise and high observation bandwidth. Therefore, fast time-varying nonlinear torque observation cannot be satisfied. To achieve this challenge, a customized network called FOESO-Net based on a novel fractional-order extended state observer is carefully designed in this paper. The network firstly chooses momentum as the benchmark state for torque estimation, which can avoid joint acceleration and model's inverse inertia matrix solution. Then, a fractional-order extended state observer (FOESO) is proposed from the perspective of momentum control to better adapt to the nonlinear fast time varying torque. In addition, a fractional-order neural network and a weight update neural network parallel architecture are constructed to enable fractional-order and dynamic weight-based adaptive learning of FOESO parameters. Formal analysis and proofs are made to show that the error of FOESO-Net is convergent. Finally, the effectiveness of the proposed method is verified by numerical simulations and a real collaborative robot platform. Moreover, compared with existing methods, the FOESO-Net based torque estimation method can reduce the estimation error and response time, which illustrates the superiority of the designed method.
Collapse
Affiliation(s)
- Shike Long
- School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin 541004, China; School of Aeronautics and Astronautics, Guilin University of Aerospace technology, Guilin 541004, China.
| | - Xuanju Dang
- School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin 541004, China.
| | - Jia Huang
- School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin 541004, China.
| |
Collapse
|
2
|
Zhang Y, Thor M, Dilokthanakul N, Dai Z, Manoonpong P. Hybrid learning mechanisms under a neural control network for various walking speed generation of a quadruped robot. Neural Netw 2023; 167:292-308. [PMID: 37666187 DOI: 10.1016/j.neunet.2023.08.030] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2022] [Revised: 06/01/2023] [Accepted: 08/18/2023] [Indexed: 09/06/2023]
Abstract
Legged robots that can instantly change motor patterns at different walking speeds are useful and can accomplish various tasks efficiently. However, state-of-the-art control methods either are difficult to develop or require long training times. In this study, we present a comprehensible neural control framework to integrate probability-based black-box optimization (PIBB) and supervised learning for robot motor pattern generation at various walking speeds. The control framework structure is based on a combination of a central pattern generator (CPG), a radial basis function (RBF) -based premotor network and a hypernetwork, resulting in a so-called neural CPG-RBF-hyper control network. First, the CPG-driven RBF network, acting as a complex motor pattern generator, was trained to learn policies (multiple motor patterns) for different speeds using PIBB. We also introduce an incremental learning strategy to avoid local optima. Second, the hypernetwork, which acts as a task/behavior to control parameter mapping, was trained using supervised learning. It creates a mapping between the internal CPG frequency (reflecting the walking speed) and motor behavior. This map represents the prior knowledge of the robot, which contains the optimal motor joint patterns at various CPG frequencies. Finally, when a user-defined robot walking frequency or speed is provided, the hypernetwork generates the corresponding policy for the CPG-RBF network. The result is a versatile locomotion controller which enables a quadruped robot to perform stable and robust walking at different speeds without sensory feedback. The policy of the controller was trained in the simulation (less than 1 h) and capable of transferring to a real robot. The generalization ability of the controller was demonstrated by testing the CPG frequencies that were not encountered during training.
Collapse
Affiliation(s)
- Yanbin Zhang
- Institute of Bio-inspired Structure and Surface Engineering, College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
| | - Mathias Thor
- Embodied AI and Neurorobotics Laboratory, SDU Biorobotics, The Mærsk Mc-Kinney Møller Institute, University of Southern Denmark, Odense M, Denmark
| | - Nat Dilokthanakul
- King Mongkut's Institute of Technology Ladkrabang, Bangkok, Thailand
| | - Zhendong Dai
- Institute of Bio-inspired Structure and Surface Engineering, College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
| | - Poramate Manoonpong
- Institute of Bio-inspired Structure and Surface Engineering, College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China; Embodied AI and Neurorobotics Laboratory, SDU Biorobotics, The Mærsk Mc-Kinney Møller Institute, University of Southern Denmark, Odense M, Denmark; Bio-inspired Robotics & Neural Engineering Laboratory, School of Information Science & Technology, Vidyasirimedhi Institute of Science & Technology, Rayong, Thailand.
| |
Collapse
|
3
|
Sun T, Dai Z, Manoonpong P. Robust and reusable self-organized locomotion of legged robots under adaptive physical and neural communications. Front Neural Circuits 2023; 17:1111285. [PMID: 37063383 PMCID: PMC10102392 DOI: 10.3389/fncir.2023.1111285] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/29/2022] [Accepted: 03/16/2023] [Indexed: 04/03/2023] Open
Abstract
IntroductionAnimals such as cattle can achieve versatile and elegant behaviors through automatic sensorimotor coordination. Their self-organized movements convey an impression of adaptability, robustness, and motor memory. However, the adaptive mechanisms underlying such natural abilities of these animals have not been completely realized in artificial legged systems.MethodsHence, we propose adaptive neural control that can mimic these abilities through adaptive physical and neural communications. The control algorithm consists of distributed local central pattern generator (CPG)-based neural circuits for generating basic leg movements, an adaptive sensory feedback mechanism for generating self-organized phase relationships among the local CPG circuits, and an adaptive neural coupling mechanism for transferring and storing the formed phase relationships (a gait pattern) into the neural structure. The adaptive neural control was evaluated in experiments using a quadruped robot.ResultsThe adaptive neural control enabled the robot to 1) rapidly and automatically form its gait (i.e., self-organized locomotion) within a few seconds, 2) memorize the gait for later recovery, and 3) robustly walk, even when a sensory feedback malfunction occurs. It also enabled maneuverability, with the robot being able to change its walking speed and direction. Moreover, implementing adaptive physical and neural communications provided an opportunity for understanding the mechanism of motor memory formation.DiscussionOverall, this study demonstrates that the integration of the two forms of communications through adaptive neural control is a powerful way to achieve robust and reusable self-organized locomotion in legged robots.
Collapse
Affiliation(s)
- Tao Sun
- Neurorobotics Technology for Advanced Robot Motor Control Lab, The College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
- Wearable Systems Lab, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China
| | - Zhendong Dai
- Neurorobotics Technology for Advanced Robot Motor Control Lab, The College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
| | - Poramate Manoonpong
- Neurorobotics Technology for Advanced Robot Motor Control Lab, The College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
- Bio-Inspired Robotics and Neural Engineering Lab, School of Information Science and Technology, Vidyasirimedhi Institute of Science and Technology, Rayong, Thailand
- *Correspondence: Poramate Manoonpong ;
| |
Collapse
|
4
|
Shao D, Wang Z, Ji A, Dai Z, Manoonpong P. A gecko-inspired robot with CPG-based neural control for locomotion and body height adaptation. BIOINSPIRATION & BIOMIMETICS 2022; 17:036008. [PMID: 35236786 DOI: 10.1088/1748-3190/ac5a3c] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/11/2021] [Accepted: 03/02/2022] [Indexed: 06/14/2023]
Abstract
Today's gecko-inspired robots have shown the ability of omnidirectional climbing on slopes with a low centre of mass. However, such an ability cannot efficiently cope with bumpy terrains or terrains with obstacles. In this study, we developed a gecko-inspired robot (Nyxbot) with an adaptable body height to overcome this limitation. Based on an analysis of the skeletal system and kinematics of real geckos, the adhesive mechanism and leg structure design of the robot were designed to endow it with adhesion and adjustable body height capabilities. Neural control with exteroceptive sensory feedback is utilised to realise body height adaptability while climbing on a slope. The locomotion performance and body adaptability of the robot were tested by conducting slope climbing and obstacle crossing experiments. The gecko robot can climb a 30° slope with spontaneous obstacle crossing (maximum obstacle height of 38% of the body height) and can climb even steeper slopes (up to 60°) without an obstacle or bump. Using 3D force measuring platforms for ground reaction force analysis of geckos and the robot, we show that the motions of the developed robot driven by neural control and the motions of geckos are dynamically comparable. To this end, this study provides a basis for developing climbing robots with adaptive bump/obstacle crossing on slopes towards more agile and versatile gecko-like locomotion.
Collapse
Affiliation(s)
- Donghao Shao
- Institute of Bio-Inspired Structure and Surface Engineering, College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, People's Republic of China
| | - Zhouyi Wang
- Institute of Bio-Inspired Structure and Surface Engineering, College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, People's Republic of China
| | - Aihong Ji
- Institute of Bio-Inspired Structure and Surface Engineering, College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, People's Republic of China
| | - Zhendong Dai
- Institute of Bio-Inspired Structure and Surface Engineering, College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, People's Republic of China
| | - Poramate Manoonpong
- Institute of Bio-Inspired Structure and Surface Engineering, College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, People's Republic of China
- Bio-Inspired Robotics and Neural Engineering Laboratory, School of Information Science and Technology, Vidyasirimedhi Institute of Science and Technology, Rayong, Thailand
- Embodied AI and Neurorobotics Laboratory, SDU Biorobotics, The Mærsk Mc-Kinney Møller Institute, University of Southern Denmark, Odense M, Denmark
| |
Collapse
|
5
|
Phodapol S, Chuthong T, Leung B, Srisuchinnawong A, Manoonpong P, Dilokthanakul N. GRAB: GRAdient-Based Shape-Adaptive Locomotion Control. IEEE Robot Autom Lett 2022. [DOI: 10.1109/lra.2021.3137555] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
|
6
|
Galljamov R, Ahmadi A, Mohseni O, Seyfarth A, Beckerle P, Sharbafi MA. Adjustable Compliance and Force Feedback as Key Elements for Stable and Efficient Hopping. IEEE Robot Autom Lett 2021. [DOI: 10.1109/lra.2021.3095024] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
|