Designing optimal soft modular robots is difficult, due to non-trivial interactions between morphology and controller. Evolutionary algorithms (EAs), combined with physical simulators, represent a valid tool to overcome this issue. In this work, we investigate algorithmic solutions to improve the Quality Diversity of co-evolved designs of Tensegrity Soft Modular Robots (TSMRs) for two robotic tasks, namely goal reaching and squeezing trough a narrow passage. To this aim, we use three different EAs, i.e., MAP-Elites and two custom algorithms: one based on Viability Evolution (ViE) and NEAT (ViE-NEAT), the other named Double Map MAP-Elites (DM-ME) and devised to seek diversity while co-evolving robot morphologies and neural network (NN)-based controllers. In detail, DM-ME extends MAP-Elites in that it uses two distinct feature maps, referring to morphologies and controllers respectively, and integrates a mechanism to automatically define the NN-related feature descriptor. Considering the fitness, in the goal-reaching task ViE-NEAT outperforms MAP-Elites and results equivalent to DM-ME. Instead, when considering diversity in terms of "illumination" of the feature space, DM-ME outperforms the other two algorithms on both tasks, providing a richer pool of possible robotic designs, whereas ViE-NEAT shows comparable performance to MAP-Elites on goal reaching, although it does not exploit any map.

An animals’ ability to learn how to make decisions based on sensory evidence is often well described by Reinforcement Learning (RL) frameworks. These frameworks, however, typically apply to event-based representations and lack the explicit and fine-grained notion of time needed to study psychophysically relevant measures like reaction times and psychometric curves. Here, we develop and use a biologically plausible continuous-time RL scheme of CT-AuGMEnT (Continuous-Time Attention-Gated MEmory Tagging) to study these behavioural quantities. We show how CT-AuGMEnT implements on-policy SARSA learning as a biologically plausible form of reinforcement learning with working memory units using ‘attentional’ feedback. We show that the CT-AuGMEnT model efficiently learns tasks in continuous time and can learn to accumulate relevant evidence through time. This allows the model to link task difficulty to psychophysical measurements such as accuracy and reaction-times. We further show how the implementation of a separate accessory network for feedback allows the model to learn continuously, also in case of significant transmission delays between the network’s feedforward and feedback layers and even when the accessory network is randomly initialized. Our results demonstrate that CT-AuGMEnT represents a fully time-continuous biologically plausible end-to-end RL model for learning to integrate evidence and make decisions.

As living organisms, one of our primary characteristics is the ability to rapidly process and react to unknown and unexpected events. To this end, we are able to recognize an event or a sequence of events and learn to respond properly. Despite advances in machine learning, current cognitive robotic systems are not able to rapidly and efficiently respond in the real world: the challenge is to learn to recognize both what is important, and also when to act. Reinforcement Learning (RL) is typically used to solve complex tasks: to learn the how. To respond quickly - to learn when - the environment has to be sampled often enough. For “enough”, a programmer has to decide on the step-size as a time-representation, choosing between a fine-grained representation of time (many state-transitions; difficult to learn with RL) or to a coarse temporal resolution (easier to learn with RL but lacking precise timing). Here, we derive a continuous-time version of on-policy SARSA-learning in a working-memory neural network model, AuGMEnT. Using a neural working memory network resolves the what problem, our when solution is built on the notion that in the real world, instantaneous actions of duration dt are actually impossible. We demonstrate how we can decouple action duration from the internal time-steps in the neural RL model using an action selection system. The resultant CT-AuGMEnT successfully learns to react to the events of a continuous-time task, without any pre-imposed specifications about the duration of the events or the delays between them.

The purpose of this work is to investigate the applicability of a visual tracking model on humanoid robots in order to achieve a human-like predictive behavior. In humans, in case of moving targets the oculomotor system uses a combination of the smooth pursuit eye movement and saccadic movements, namely “catch up” saccades to fixate the object of interest. This work aims to validate the "catch up" saccade model in order to obtain a human-like tracking system able to correctly switch from a zero-lag predictive smooth pursuit to a fast orienting saccade for the position error compensation. Experimental results on the iCub simulator show several correspondences with the human behavior.