Learning Modular Robot Control Policies

Whitman, Julian; Travers, Matthew; Choset, Howie

doi:10.1109/tro.2023.3284362

Cited by 18 publications

(3 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various researchers have worked on the development of evolutionary algorithms to generate control methods for modular robots [9]. Other works have proposed optimization methods for control parameters for each module of modular robot manipulators [10] and the generation of control policies and configuration design using reinforcement learning algorithms [11,12]. In the field of underwater modular robots that we address in this study, Doyle et al have proposed modular fluidic propulsion (MFP) [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fault-Tolerant Phototaxis of a Modular System Inspired by Gonium pectorale Using Phase-Based Control

Nishikawa,

Origane,

Etchu

et al. 2024

Symmetry

View full text Add to dashboard Cite

In this study, we proposed a model for modular robots in which autonomous decentralized modules adaptively organize their behavior. The phototaxis of Gonium pectorale, a species of volvocine algae, was modeled as a modular system, and a fault-tolerant modular control method of phototaxis was proposed for it. The proposed method was based on the rotation phase of the colony and adaptively adjusted an internal response-related parameter to enhance the fault tolerance of the system. Compared to a constant parameter approach, the simulation results demonstrated a significant improvement in the phototaxis time for positive and negative phototaxis during module failures. This method contributes to achieving autonomous, decentralized, and purposeful mediation of the modules necessary for controlling modular robots.

show abstract

Section: Introductionmentioning

confidence: 99%

“…This research proposed autonomous distributed control rules for modules. Some works interpreted module configurations as graph structures for kinematics analysis or machine learning [11,14].…”

Section: Introductionmentioning

confidence: 99%

Fault-Tolerant Phototaxis of a Modular System Inspired by Gonium pectorale Using Phase-Based Control

Nishikawa,

Origane,

Etchu

et al. 2024

Symmetry

View full text Add to dashboard Cite

show abstract

“…A common usage is to define individual modules as nodes and modules’ connectivity relationships with each other as edges. 21 The position of the node can be represented by a Cartesian coordinate system and the change in connectivity can be represented by a change in the state of the edge. Then the reconfiguration strategies can be designed under the system graph.…”

Section: Introductionmentioning

confidence: 99%

A novel distributed meta-module motion design for modular robotic systems based on grid partition method

Guan,

Wang,

Zhang

et al. 2024

Science Progress

View full text Add to dashboard Cite

This article studies a meta-module motion design approach for homogenous modular robotic systems in self-configuration. By utilizing configuration diversity, scalability and unit-substitutability, homogenous modular robotic systems can be a promising approach to life detection and space exploration in the future. Based on the requirements of the potential applications, self-configuration can be considered as the precondition. As similar to swarm robotic systems, the distributed control strategy in which the modular robots are operated in a sequence of motion circles consist of ‘detection’– ‘decision’– ‘execution’ is of great significance. However, there is a limitation to the applicability of previously proposed work on the self-configuration topic, due to the fact that the self-configuration strategy execution suffers from the motion constraints of modular robots. In order to solve the problem, we propose a grid partition method that removes the gap between the locomotion of a single modular robot and the reconfiguration of the whole system. Under the analysis of the grid partition, the meta-module motion design is proposed to realize the distributed self-configuration strategy. We simulated the self-configuration in M-Lattice, a two-dimensional homogenous modular robotic system.

show abstract

Totipotent neural controllers for modular soft robots: Achieving specialization in body–brain co-evolution through Hebbian learning

Ferigo,

Iacca,

Medvet

et al. 2025

Neurocomputing

View full text Add to dashboard Cite

Learning Modular Robot Control Policies

Cited by 18 publications

References 52 publications

Fault-Tolerant Phototaxis of a Modular System Inspired by Gonium pectorale Using Phase-Based Control

Fault-Tolerant Phototaxis of a Modular System Inspired by Gonium pectorale Using Phase-Based Control

A novel distributed meta-module motion design for modular robotic systems based on grid partition method

Totipotent neural controllers for modular soft robots: Achieving specialization in body–brain co-evolution through Hebbian learning

Contact Info

Product

Resources

About