1
|
van Diggelen F, Cambier N, Ferrante E, Eiben AE. A model-free method to learn multiple skills in parallel on modular robots. Nat Commun 2024; 15:6267. [PMID: 39048541 PMCID: PMC11269725 DOI: 10.1038/s41467-024-50131-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2024] [Accepted: 07/02/2024] [Indexed: 07/27/2024] Open
Abstract
Legged robots are well-suited for deployment in unstructured environments but require a unique control scheme specific for their design. As controllers optimised in simulation do not transfer well to the real world (the infamous sim-to-real gap), methods enabling quick learning in the real world, without any assumptions on the specific robot model and its dynamics, are necessary. In this paper, we present a generic method based on Central Pattern Generators, that enables the acquisition of basic locomotion skills in parallel, through very few trials. The novelty of our approach, underpinned by a mathematical analysis of the controller model, is to search for good initial states, instead of optimising connection weights. Empirical validation in six different robot morphologies demonstrates that our method enables robots to learn primary locomotion skills in less than 15 minutes in the real world. In the end, we showcase our skills in a targeted locomotion experiment.
Collapse
Affiliation(s)
- Fuda van Diggelen
- Department of Computer Science, Vrije Universiteit Amsterdam, Amsterdam, Noord-Holland, the Netherlands.
| | - Nicolas Cambier
- Department of Computer Science, Vrije Universiteit Amsterdam, Amsterdam, Noord-Holland, the Netherlands
| | - Eliseo Ferrante
- Department of Computer Science, Vrije Universiteit Amsterdam, Amsterdam, Noord-Holland, the Netherlands
| | - A E Eiben
- Department of Computer Science, Vrije Universiteit Amsterdam, Amsterdam, Noord-Holland, the Netherlands
| |
Collapse
|
2
|
Kuckling J. Recent trends in robot learning and evolution for swarm robotics. Front Robot AI 2023; 10:1134841. [PMID: 37168882 PMCID: PMC10166233 DOI: 10.3389/frobt.2023.1134841] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2022] [Accepted: 03/21/2023] [Indexed: 05/13/2023] Open
Abstract
Swarm robotics is a promising approach to control large groups of robots. However, designing the individual behavior of the robots so that a desired collective behavior emerges is still a major challenge. In recent years, many advances in the automatic design of control software for robot swarms have been made, thus making automatic design a promising tool to address this challenge. In this article, I highlight and discuss recent advances and trends in offline robot evolution, embodied evolution, and offline robot learning for swarm robotics. For each approach, I describe recent design methods of interest, and commonly encountered challenges. In addition to the review, I provide a perspective on recent trends and discuss how they might influence future research to help address the remaining challenges of designing robot swarms.
Collapse
|
3
|
On Using Simulation to Predict the Performance of Robot Swarms. Sci Data 2022; 9:788. [PMID: 36581617 PMCID: PMC9800372 DOI: 10.1038/s41597-022-01895-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2022] [Accepted: 12/12/2022] [Indexed: 12/31/2022] Open
Abstract
The discrepancy between simulation and reality-known as the reality gap-is one of the main challenges associated with using simulations to design control software for robot swarms. Currently, the reality-gap problem necessitates expensive and time consuming tests on physical robots to reliably assess control software. Predicting real-world performance accurately without recurring to physical experiments would be particularly valuable. In this paper, we compare various simulation-based predictors of the performance of robot swarms that have been proposed in the literature but never evaluated empirically. We consider (1) the classical approach adopted to estimate real-world performance, which relies on the evaluation of control software on the simulation model used in the design process, and (2) some so-called pseudo-reality predictors, which rely on simulation models other than the one used in the design process. To evaluate these predictors, we reuse 1021 instances of control software and their real-world performance gathered from seven previous studies. Results show that the pseudo-reality predictors considered yield more accurate estimates of the real-world performance than the classical approach.
Collapse
|
4
|
Bozhinoski D, Birattari M. Towards an integrated automatic design process for robot swarms. OPEN RESEARCH EUROPE 2022; 1:112. [PMID: 37645125 PMCID: PMC10446085 DOI: 10.12688/openreseurope.14025.2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Accepted: 08/05/2022] [Indexed: 08/31/2023]
Abstract
Background: The specification of missions to be accomplished by a robot swarm has been rarely discussed in the literature: designers do not follow any standardized processes or use any tool to precisely define a mission that must be accomplished. Methods: In this paper, we introduce a fully integrated design process that starts with the specification of a mission to be accomplished and terminates with the deployment of the robots in the target environment. We introduce Swarm Mission Language (SML), a textual language that allows swarm designers to specify missions. Using model-driven engineering techniques, we define a process that automatically transforms a mission specified in SML into a configuration setup for an optimization-based design method. Upon completion, the output of the optimization-based design method is an instance of control software that is eventually deployed on real robots. Results: We demonstrate the fully integrated process we propose on three different missions. Conclusions: We aim to show that in order to create reliable, maintainable and verifiable robot swarms, swarm designers may benefit from following standardised automatic design processes that will facilitate the design of control software in all stages of the development.
Collapse
|
5
|
Bozhinoski D, Birattari M. Towards an integrated automatic design process for robot swarms. OPEN RESEARCH EUROPE 2022; 1:112. [PMID: 37645125 PMCID: PMC10446085 DOI: 10.12688/openreseurope.14025.1] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Accepted: 08/05/2022] [Indexed: 08/31/2023]
Abstract
Background: The specification of missions to be accomplished by a robot swarm has been rarely discussed in the literature: designers do not follow any standardized processes or use any tool to precisely define a mission that must be accomplished. Methods: In this paper, we introduce a fully integrated design process that starts with the specification of a mission to be accomplished and terminates with the deployment of the robots in the target environment. We introduce Swarm Mission Language (SML), a textual language that allows swarm designers to specify missions. Using model-driven engineering techniques, we define a process that automatically transforms a mission specified in SML into a configuration setup for an optimization-based design method. Upon completion, the output of the optimization-based design method is an instance of control software that is eventually deployed on real robots. Results: We demonstrate the fully integrated process we propose on three different missions. Conclusions: We aim to show that in order to create reliable, maintainable and verifiable robot swarms, swarm designers may benefit from following standardised automatic design processes that will facilitate the design of control software in all stages of the development.
Collapse
|
6
|
Simulation of Automatic Color Adjustment of Landscape Image Based on Color Mapping Algorithm. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2022; 2022:7663659. [PMID: 35875773 PMCID: PMC9303091 DOI: 10.1155/2022/7663659] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/22/2022] [Revised: 06/17/2022] [Accepted: 06/24/2022] [Indexed: 11/18/2022]
Abstract
With the continuous development and progress of image sensing technology in recent years, the problem of image data acquisition, recovery, and recording has been solved, and people have gradually realized that image data can be better recovered, recorded, and exhibited by collecting image data. It is also used in target recognition, image display, landscape design, and other fields. And the application of color mapping algorithm can more intuitively affect the final quality of the display image. This is extremely important for landscape design. It can be said that the emergence and application of color mapping algorithm provide strong technical support for both dynamic and static image color automatic adjustment and simulation. On this basis, taking the color mapping algorithm as the breakthrough, through the in-depth introduction of the color mapping algorithm, starting from the direction of landscape image color automatic adjustment, a relatively simplified color mapping algorithm model inheriting the positive and negative two-way vision model is proposed. At the same time, a simulation algorithm based on landscape suitcase color automatic adjustment is proposed based on the color mapping algorithm model. Experiments show that automatic color adjustment of landscape images based on color mapping algorithm can achieve more realistic image reproduction, and the color mapping method based on color mapping algorithm has less illumination bias. When the number of experiments is 30, the difference in visibility of the plane is 0.25 cd/m2, the difference of visibility according to the color change segmented by the gradient area is 0.71 cd/m2, and the difference of the illuminance difference of the transition image is 0.71 cd/m2. Gaussian pyramid is 1.25 cd/m2. The proposed method improves color density by reducing image sharpness and compensating for color sharpness of landscape image, and high quality landscape images provide assistance for landscape design.
Collapse
|
7
|
Hasselmann K, Ligot A, Ruddick J, Birattari M. Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms. Nat Commun 2021; 12:4345. [PMID: 34272382 PMCID: PMC8285396 DOI: 10.1038/s41467-021-24642-3] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/25/2021] [Accepted: 06/23/2021] [Indexed: 11/23/2022] Open
Abstract
Neuro-evolution is an appealing approach to generating collective behaviors for robot swarms. In its typical application, known as off-line automatic design, the neural networks controlling the robots are optimized in simulation. It is understood that the so-called reality gap, the unavoidable differences between simulation and reality, typically causes neural network to be less effective on real robots than what is predicted by simulation. In this paper, we present an empirical study on the extent to which the reality gap impacts the most popular and advanced neuro-evolutionary methods for the off-line design of robot swarms. The results show that the neural networks produced by the methods under analysis performed well in simulation, but not in real-robot experiments. Further, the ranking that could be observed in simulation between the methods eventually disappeared. We find compelling evidence that real-robot experiments are needed to reliably assess the performance of neuro-evolutionary methods and that the robustness to the reality gap is the main issue to be addressed to advance the application of neuro-evolution to robot swarms.
Collapse
Affiliation(s)
- Ken Hasselmann
- IRIDIA, Université libre de Bruxelles, Brussels, Belgium
| | - Antoine Ligot
- IRIDIA, Université libre de Bruxelles, Brussels, Belgium
| | - Julian Ruddick
- IRIDIA, Université libre de Bruxelles, Brussels, Belgium
| | | |
Collapse
|
8
|
Kuckling J, Stützle T, Birattari M. Iterative improvement in the automatic modular design of robot swarms. PeerJ Comput Sci 2020; 6:e322. [PMID: 33816972 PMCID: PMC7924708 DOI: 10.7717/peerj-cs.322] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/03/2020] [Accepted: 11/06/2020] [Indexed: 05/26/2023]
Abstract
Iterative improvement is an optimization technique that finds frequent application in heuristic optimization, but, to the best of our knowledge, has not yet been adopted in the automatic design of control software for robots. In this work, we investigate iterative improvement in the context of the automatic modular design of control software for robot swarms. In particular, we investigate the optimization of two control architectures: finite-state machines and behavior trees. Finite state machines are a common choice for the control architecture in swarm robotics whereas behavior trees have received less attention so far. We compare three different optimization techniques: iterative improvement, Iterated F-race, and a hybridization of Iterated F-race and iterative improvement. For reference, we include in our study also (i) a design method in which behavior trees are optimized via genetic programming and (ii) EvoStick, a yardstick implementation of the neuro-evolutionary swarm robotics approach. The results indicate that iterative improvement is a viable optimization algorithm in the automatic modular design of control software for robot swarms.
Collapse
Affiliation(s)
- Jonas Kuckling
- IRIDIA, Université Libre de Bruxelles, Brussels, Belgium
| | - Thomas Stützle
- IRIDIA, Université Libre de Bruxelles, Brussels, Belgium
| | | |
Collapse
|
9
|
Ligot A, Kuckling J, Bozhinoski D, Birattari M. Automatic modular design of robot swarms using behavior trees as a control architecture. PeerJ Comput Sci 2020; 6:e314. [PMID: 33816965 PMCID: PMC7924474 DOI: 10.7717/peerj-cs.314] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2020] [Accepted: 10/16/2020] [Indexed: 05/26/2023]
Abstract
We investigate the possibilities, challenges, and limitations that arise from the use of behavior trees in the context of the automatic modular design of collective behaviors in swarm robotics. To do so, we introduce Maple, an automatic design method that combines predefined modules-low-level behaviors and conditions-into a behavior tree that encodes the individual behavior of each robot of the swarm. We present three empirical studies based on two missions: aggregation and Foraging. To explore the strengths and weaknesses of adopting behavior trees as a control architecture, we compare Maple with Chocolate, a previously proposed automatic design method that uses probabilistic finite state machines instead. In the first study, we assess Maple's ability to produce control software that crosses the reality gap satisfactorily. In the second study, we investigate Maple's performance as a function of the design budget, that is, the maximum number of simulation runs that the design process is allowed to perform. In the third study, we explore a number of possible variants of Maple that differ in the constraints imposed on the structure of the behavior trees generated. The results of the three studies indicate that, in the context of swarm robotics, behavior trees might be appealing but in many settings do not produce better solutions than finite state machines.
Collapse
Affiliation(s)
- Antoine Ligot
- IRIDIA, Université Libre de Bruxelles, Brussels, Belgium
| | - Jonas Kuckling
- IRIDIA, Université Libre de Bruxelles, Brussels, Belgium
| | - Darko Bozhinoski
- IRIDIA, Université Libre de Bruxelles, Brussels, Belgium
- Cognitive Robotics, Delft University of Technology, Delft, Netherlands
| | | |
Collapse
|
10
|
Hasselmann K, Birattari M. Modular automatic design of collective behaviors for robots endowed with local communication capabilities. PeerJ Comput Sci 2020; 6:e291. [PMID: 33816942 PMCID: PMC7924432 DOI: 10.7717/peerj-cs.291] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2020] [Accepted: 07/20/2020] [Indexed: 05/26/2023]
Abstract
We investigate the automatic design of communication in swarm robotics through two studies. We first introduce Gianduja an automatic design method that generates collective behaviors for robot swarms in which individuals can locally exchange a message whose semantics is not a priori fixed. It is the automatic design process that, on a per-mission basis, defines the conditions under which the message is sent and the effect that it has on the receiving peers. Then, we extend Gianduja to Gianduja2 and Gianduja 3, which target robots that can exchange multiple distinct messages. Also in this case, the semantics of the messages is automatically defined on a per-mission basis by the design process. Gianduja and its variants are based on Chocolate, which does not provide any support for local communication. In the article, we compare Gianduja and its variants with a standard neuro-evolutionary approach. We consider a total of six different swarm robotics missions. We present results based on simulation and tests performed with 20 e-puck robots. Results show that, typically, Gianduja and its variants are able to associate a meaningful semantics to messages.
Collapse
Affiliation(s)
- Ken Hasselmann
- IRIDIA, Université Libre de Bruxelles, Brussels, Belgium
| | | |
Collapse
|
11
|
Automatic Design of Collective Behaviors for Robots that Can Display and Perceive Colors. APPLIED SCIENCES-BASEL 2020. [DOI: 10.3390/app10134654] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Research in swarm robotics has shown that automatic design is an effective approach to realize robot swarms. In automatic design methods, the collective behavior of a swarm is obtained by automatically configuring and fine-tuning the control software of individual robots. In this paper, we present TuttiFrutti: an automatic design method for robot swarms that belongs to AutoMoDe—a family of methods that produce control software by assembling preexisting software modules via optimization. The peculiarity of TuttiFrutti is that it designs control software for e-puck robots that can display and perceive colors using their RGB LEDs and omnidirectional camera. Studies with AutoMoDe have been so far restricted by the limited capabilities of the e-pucks. By enabling the use of colors, we significantly enlarge the variety of collective behaviors they can produce. We assess TuttiFrutti with swarms of e-pucks that perform missions in which they should react to colored light. Results show that TuttiFrutti designs collective behaviors in which the robots identify the colored light displayed in the environment and act accordingly. The control software designed by TuttiFrutti endowed the swarms of e-pucks with the ability to use color-based information for handling events, communicating, and navigating.
Collapse
|
12
|
Roli A, Ligot A, Birattari M. Complexity Measures: Open Questions and Novel Opportunities in the Automatic Design and Analysis of Robot Swarms. Front Robot AI 2019; 6:130. [PMID: 33501145 PMCID: PMC7805888 DOI: 10.3389/frobt.2019.00130] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/12/2018] [Accepted: 11/11/2019] [Indexed: 11/13/2022] Open
Abstract
Complexity measures and information theory metrics in general have recently been attracting the interest of multi-agent and robotics communities, owing to their capability of capturing relevant features of robot behaviors, while abstracting from implementation details. We believe that theories and tools from complex systems science and information theory may be fruitfully applied in the near future to support the automatic design of robot swarms and the analysis of their dynamics. In this paper we discuss opportunities and open questions in this scenario.
Collapse
Affiliation(s)
- Andrea Roli
- Department of Computer Science and Engineering, Campus of Cesena, Alma Mater Studiorum Università di Bologna, Bologna, Italy
| | - Antoine Ligot
- IRIDIA, Université libre de Bruxelles, Brussels, Belgium
| | | |
Collapse
|