Evolutionary Robotics and the Radical Envelope-of-Noise Hypothesis

Jakobi, Nick

doi:10.1177/105971239700600205

Cited by 209 publications

(201 citation statements)

References 13 publications

Supporting

Mentioning

199

Contrasting

Order By: Relevance

“…The robot and its world are simulated using the "minimal simulation" technique described in [6]. This technique uses high levels of noise to guarantee that the simulated controller transfers to the physical robot with no loss of performance (see [1]).…”

Section: Methodsmentioning

confidence: 99%

Evolving Neural Mechanisms for an Iterated Discrimination Task: A Robot Based Model

Tuci

Ampatzis

Dorigo

2005

Advances in Artificial Life

View full text Add to dashboard Cite

Abstract. This paper is about the design of an artificial neural network to control an autonomous robot that is required to iteratively solve a discrimination task based on time-dependent structures. The "decision making" aspect demands the robot "to decide", during a sequence of trials, whether or not the type of environment it encounters allows it to reach a light bulb located at the centre of a simulated world. Contrary to other similar studies, in this work the robot employs environmental structures to iteratively make its choice, without previous experience disrupting the functionality of its decision-making mechanisms.

show abstract

Section: Methodsmentioning

confidence: 99%

Evolving Neural Mechanisms for an Iterated Discrimination Task: A Robot Based Model

Tuci

Ampatzis

Dorigo

2005

Advances in Artificial Life

View full text Add to dashboard Cite

show abstract

“…ER experiments sometimes evolve relatively trivial solutions for tasks that researchers had intended to entail a higher level of complexity. For example, the T-maze has solutions that do not require memory [52,69]. Similarly, many benchmark ER tasks may have algorithmically simple, but possibly very obscure, solutions that are not obvious to designers, but which evolutionary searches can find in what essentially amount to extended optimization processes.…”

Section: A Benchmark Er Tasks Don't Represent the General Casementioning

confidence: 99%

“…This often takes the form of a rodent T-maze [52]. A standard T-maze may be equipped with two signal stations separated both from each other (either spatially or temporally) and from the T intersection (the memory-T-maze) [65,66].…”

Section: B T-mazementioning

confidence: 99%

“…Many of the now standard test scenarios were developed and extensively explored during this time. These include navigation with obstacle avoidance and target homing [50,51], foraging [7], differential navigation with memory [52], gait learning in legged robots [44,53], coevolution of morphology and control for locomotion [54], and pursuit and evasion, usually formulated in terms of coevolution of populations [38,39,55].…”

Section: Background and Historymentioning

confidence: 99%

See 1 more Smart Citation

Embodied artificial life at an impasse can evolutionary robotics methods be scaled?

Nelson¹

2014

2014 IEEE Symposium on Evolving and Autonomous Learning Systems (EALS)

View full text Add to dashboard Cite

Abstract-Evolutionary robotics (ER) investigates the application of artificial evolution toward the synthesis of robots capable of performing autonomous behaviors. Over the last 25 years, researchers have reported increasingly complex evolved behaviors, and have compiled a de facto set of benchmark tasks. Perhaps the best known of these is the obstacle avoidance and target homing task performed by differential drive robots. More complex tasks studied in recent ER work include augmented variants of the rodent T-maze and complex foraging tasks. But can proof-of-concept results such as these be extended to evolve complex autonomous behaviors in a general sense? In this topical analysis paper we survey relevant research and make the case that common tasks used to demonstrate the effectiveness of evolutionary robotics are not characteristic of more general cases and in fact do not fully prove the concept that artificial evolution can be used to evolve sophisticated autonomous agent behaviors. Robots capable of performing many of the tasks studied in ER have now been evolved using nearly aggregate binary success/fail fitness functions. However, arguments used to support the necessity of incremental methods for complex tasks are essentially sound. This raises the possibility that the tasks themselves allow for relatively simple solutions, or span a relatively small candidate solution set. This paper presents these arguments in detail and concludes with a discussion of current ER research.

show abstract

“…In [14], the author claims that the robot does not have to move identically in simulation and reality in order for the porting to be called successful, but its behaviour has to satisfy some criteria defined by the experimenter. Following this principle, real robots are considered successful if they carry out the main requirements of our task.…”

Section: Porting On Real Robotsmentioning

confidence: 99%

Evolution of Signalling in a Group of Robots Controlled by Dynamic Neural Networks

et al.

View full text Add to dashboard Cite

Abstract. Communication is a point of central importance in swarms of robots. This paper describes a set of simulations in which artificial evolution is used as a means to engineer robot neuro-controllers capable of guiding groups of robots in a categorisation task by producing appropriate actions. Communicative behaviour emerges, notwithstanding the absence of explicit selective pressure (coded into the fitness function) to favour signalling over non-signalling groups. Post-evaluation analyses illustrate the adaptive function of the evolved signals and show that they are tightly linked to the behavioural repertoire of the agents. Finally, our approach for developing controllers is validated by successfully porting one evolved controller on real robots.

show abstract

Evolutionary Robotics and the Radical Envelope-of-Noise Hypothesis

Cited by 209 publications

References 13 publications

Evolving Neural Mechanisms for an Iterated Discrimination Task: A Robot Based Model

Evolving Neural Mechanisms for an Iterated Discrimination Task: A Robot Based Model

Embodied artificial life at an impasse can evolutionary robotics methods be scaled?

Evolution of Signalling in a Group of Robots Controlled by Dynamic Neural Networks

Contact Info

Product

Resources

About