Wankelmut: A Simple Benchmark for the Evolvability of Behavioral Complexity

Thomas Schmickl; Payam Zahadat; Heiko Hamann

doi:10.3390/app11051994

Wankelmut: A Simple Benchmark for the Evolvability of Behavioral Complexity

Applied Sciences ◽

10.3390/app11051994 ◽

2021 ◽

Vol 11 (5) ◽

pp. 1994

Author(s):

Thomas Schmickl ◽

Payam Zahadat ◽

Heiko Hamann

Keyword(s):

Neural Networks ◽

Evolutionary Computation ◽

A Priori ◽

Evolutionary Process ◽

Evolutionary Robotics ◽

Sensor Data ◽

Control Software ◽

Main Claim ◽

Behavioral Complexity ◽

Model Free

In evolutionary robotics, an encoding of the control software that maps sensor data (input) to motor control values (output) is shaped by stochastic optimization methods to complete a predefined task. This approach is assumed to be beneficial compared to standard methods of controller design in those cases where no a priori model is available that could help to optimize performance. For robots that have to operate in unpredictable environments as well, an evolutionary robotics approach is favorable. We present here a simple-to-implement, but hard-to-pass benchmark to allow for quantifying the “evolvability” of such evolving robot control software towards increasing behavioral complexity. We demonstrate that such a model-free approach is not a free lunch, as already simple tasks can be unsolvable barriers for fully open-ended uninformed evolutionary computation techniques. We propose the “Wankelmut” task as an objective for an evolutionary approach that starts from scratch without pre-shaped controller software or any other informed approach that would force the behavior to be evolved in a desired way. Our main claim is that “Wankelmut” represents the simplest set of problems that makes plain-vanilla evolutionary computation fail. We demonstrate this by a series of simple standard evolutionary approaches using different fitness functions and standard artificial neural networks, as well as continuous-time recurrent neural networks. All our tested approaches failed. From our observations, we conclude that other evolutionary approaches will also fail if they do not per se favor or enforce the modularity of the evolved structures and if they do not freeze or protect already evolved functionalities from being destroyed again in the later evolutionary process. However, such a protection would require a priori knowledge of the solution of the task and contradict the “no a priori model” approach that is often claimed in evolutionary computation. Thus, we propose a hard-to-pass benchmark in order to make a strong statement for self-complexifying and generative approaches in evolutionary computation in general and in evolutionary robotics specifically. We anticipate that defining such a benchmark by seeking the simplest task that causes the evolutionary process to fail can be a valuable benchmark for promoting future development in the fields of artificial intelligence, evolutionary robotics, and artificial life.

Download Full-text

Engineering the Evolution of Self-Organizing Behaviors in Swarm Robotics: A Case Study

Artificial Life ◽

10.1162/artl_a_00031 ◽

2011 ◽

Vol 17 (3) ◽

pp. 183-202 ◽

Cited By ~ 39

Author(s):

Vito Trianni ◽

Stefano Nolfi

Keyword(s):

Communication System ◽

Swarm Robotics ◽

A Priori ◽

Evolutionary Process ◽

Deep Understanding ◽

Evolutionary Robotics ◽

Powerful Approach ◽

Large Groups ◽

Self Organizing

Evolutionary robotics (ER) is a powerful approach for the automatic synthesis of robot controllers, as it requires little a priori knowledge about the problem to be solved in order to obtain good solutions. This is particularly true for collective and swarm robotics, in which the desired behavior of the group is an indirect result of the control and communication rules followed by each individual. However, the experimenter must make several arbitrary choices in setting up the evolutionary process, in order to define the correct selective pressures that can lead to the desired results. In some cases, only a deep understanding of the obtained results can point to the critical aspects that constrain the system, which can be later modified in order to re-engineer the evolutionary process towards better solutions. In this article, we discuss the problem of engineering the evolutionary machinery that can lead to the desired result in the swarm robotics context. We also present a case study about self-organizing synchronization in a swarm of robots, in which some arbitrarily chosen properties of the communication system hinder the scalability of the behavior to large groups. We show that by modifying the communication system, artificial evolution can synthesize behaviors that scale properly with the group size.

Download Full-text

Augmenting Scalable Communication-Based Role Allocation for a Three-Role Task

INTELIGENCIA ARTIFICIAL ◽

10.4114/intartif.vol22iss64pp152-165 ◽

2020 ◽

Vol 22 (64) ◽

pp. 152-165

Author(s):

Gustavo Martins ◽

Paulo Urbano ◽

Anders Lyhne Christensen

Keyword(s):

Fitness Function ◽

A Priori ◽

Evolutionary Process ◽

Evolutionary Robotics ◽

Cognitive Architectures ◽

Local Conditions ◽

Fitness Functions ◽

Signal Differentiation ◽

Scalable Communication ◽

Role Allocation

In evolutionary robotics role allocation studies, it is common that the role assumed by each robot is strongly associated with specific local conditions, which may compromise scalability and robustness because of the dependency on those conditions. To increase scalability, communication has been proposed as a means for robots to exchange signals that represent roles. This idea was successfully applied to evolve communication-based role allocation for a two-role task. However, it was necessary to reward signal differentiation in the fitness function, which is a serious limitation as it does not generalize to tasks where the number of roles is unknown a priori. In this paper, we show that rewarding signal differentiation is not necessary to evolve communication-based role allocation strategies for the given task, and we improve reported scalability, while requiring less a priori knowledge. Our approach for the two-role task puts fewer constrains on the evolutionary process and enhances the potential of evolving communication-based role allocation for more complex tasks. Furthermore, we conduct experiments for a three-role task where we compare two different cognitive architectures and several fitness functions and we show how scalable controllers might be evolved.

Download Full-text

Deep Convolutional Neural Network with RNNs for Complex Activity Recognition Using Wrist-Worn Wearable Sensor Data

Electronics ◽

10.3390/electronics10141685 ◽

2021 ◽

Vol 10 (14) ◽

pp. 1685

Author(s):

Sakorn Mekruksavanich ◽

Anuchit Jitpattanakul

Keyword(s):

Neural Networks ◽

Activity Recognition ◽

Human Activities ◽

Recognition Performance ◽

Confusion Matrix ◽

Experimental Studies ◽

Industrial Applications ◽

Sensor Data ◽

Complex Activity ◽

Activity Data

Sensor-based human activity recognition (S-HAR) has become an important and high-impact topic of research within human-centered computing. In the last decade, successful applications of S-HAR have been presented through fruitful academic research and industrial applications, including for healthcare monitoring, smart home controlling, and daily sport tracking. However, the growing requirements of many current applications for recognizing complex human activities (CHA) have begun to attract the attention of the HAR research field when compared with simple human activities (SHA). S-HAR has shown that deep learning (DL), a type of machine learning based on complicated artificial neural networks, has a significant degree of recognition efficiency. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are two different types of DL methods that have been successfully applied to the S-HAR challenge in recent years. In this paper, we focused on four RNN-based DL models (LSTMs, BiLSTMs, GRUs, and BiGRUs) that performed complex activity recognition tasks. The efficiency of four hybrid DL models that combine convolutional layers with the efficient RNN-based models was also studied. Experimental studies on the UTwente dataset demonstrated that the suggested hybrid RNN-based models achieved a high level of recognition performance along with a variety of performance indicators, including accuracy, F1-score, and confusion matrix. The experimental results show that the hybrid DL model called CNN-BiGRU outperformed the other DL models with a high accuracy of 98.89% when using only complex activity data. Moreover, the CNN-BiGRU model also achieved the highest recognition performance in other scenarios (99.44% by using only simple activity data and 98.78% with a combination of simple and complex activities).

Download Full-text

Adaptive Multi-Sensor Data Fusion Positioning Algorithm Based On Long Short Term Memory Neural Networks

2020 IEEE 20th International Conference on Communication Technology (ICCT) ◽

10.1109/icct50939.2020.9295914 ◽

2020 ◽

Author(s):

Jie Zhou ◽

Guanghui Xu ◽

Donglin Zhu ◽

Enbiao Di

Keyword(s):

Neural Networks ◽

Data Fusion ◽

Short Term Memory ◽

Sensor Data ◽

Short Term ◽

Term Memory ◽

Sensor Data Fusion ◽

Multi Sensor Data Fusion ◽

Long Short Term Memory ◽

Positioning Algorithm

Download Full-text

Optical Axons for Electro-Optical Neural Networks

Sensors ◽

10.3390/s20216119 ◽

2020 ◽

Vol 20 (21) ◽

pp. 6119

Author(s):

Mircea Hulea ◽

Zabih Ghassemlooy ◽

Sujan Rajbhandari ◽

Othman Isam Younus ◽

Alexandru Barleanu

Keyword(s):

Neural Networks ◽

Optical Signal ◽

Sensor Data ◽

Line Of Sight ◽

Optical Intensity ◽

Digital Signals ◽

Link Length ◽

Optical Neural Networks ◽

Analogue Signals ◽

Neural Unit

Recently, neuromorphic sensors, which convert analogue signals to spiking frequencies, have been reported for neurorobotics. In bio-inspired systems these sensors are connected to the main neural unit to perform post-processing of the sensor data. The performance of spiking neural networks has been improved using optical synapses, which offer parallel communications between the distanced neural areas but are sensitive to the intensity variations of the optical signal. For systems with several neuromorphic sensors, which are connected optically to the main unit, the use of optical synapses is not an advantage. To address this, in this paper we propose and experimentally verify optical axons with synapses activated optically using digital signals. The synaptic weights are encoded by the energy of the stimuli, which are then optically transmitted independently. We show that the optical intensity fluctuations and link’s misalignment result in delay in activation of the synapses. For the proposed optical axon, we have demonstrated line of sight transmission over a maximum link length of 190 cm with a delay of 8 μs. Furthermore, we show the axon delay as a function of the illuminance using a fitted model for which the root mean square error (RMS) similarity is 0.95.

Download Full-text