Reinforcement Learning framework for Robotics

Cognitive Robot Abstract Machine in Python

VU-CLTL Pepper/Nao Application Repository (Python 2)

This repository is a new wearable biosensors package for ROS2-Foxy. The ultimate goal of this repo is to expand the biosensors ecosystem in the Human-Robot Interaction (HRI) field. The package currently supports six wearable biosensors that can be used in HRI researches without behavioral constraints caused by limited hardware specifications (e.g., wired devices). We will keep updating this GitHub to support various wearable sensors on ROS 2 system. If you are interested in this project, please contact us.

Angular JS K9 robot controller, designed primarily for use on a iPad or Android touch device as a virtual joystick. Also visualizes the robot's surroundings using camera and sensor data.

Public knowledge, help, code, contributions and projects about how to work with Softbank Robotics' Pepper robot model

Pepper implementation of the cognitive architecture for Trust and Theory of Mind in humanoid robots applied to Vanderbilt's experiment.

quantum-robot: Quantum-Like perception modelling in Python

ROS implementation of shopping bot manager on Pepper. This is for an university project.

State Estimation of an Agent using Observations | AI for Cognitive Robot Intelligence @ IIT Delhi

Python for Cognitive Robotics mind map

Intelligent Social Systems and Swarm Robotics Lab (IS3R)

Code for Special Issue on “Cognitive architectures for Reinforcement Learning”, Cognitive Systems Research

An innovative multi-task neural architecture suitable for face analysis and the consequent identification of gender, age, ethnicity and emotion. A network capable of the performance of the state of the art of single-task networks by sharing the feature extraction part. It may be suitable for robotic applications: it requires time and memory in the order of a single-task network.

This repository provides the content of the ICDL tutorial, we use a Docker-based environment to integrate infant behavior models using the CST (Cognitive System Toolkit). Tutorial presented at the ICDL (International Conference on Development and Learning).

PhD project repository. CogScore - An Online Evaluation Playground For Cognitive Architectures With Developmental Robotics. This work aims to present a general framework for the automated evaluation of different levels of diverse cognitive capabilities of cognitive architectures.

Supplementary material for the paper "Commonsense Knowledge in Cognitive Robotics: A Systematic Literature Review"

A Trees on Manifolds approach to N-Gram predictors on Monte Carlo Geometric Parsings of Dirichlet Domains

Thesis Project: A multimodal transformer-based generative model that creates listener avatars conditioned on personality traits to produce realistic non-verbal responses (facial expressions, body and hand gestures), during dyadic conversations. Built with PyTorch, and trained on UDIVA dataset, achieving state-of-the-art FID/P-FID performance.

PhD project page. CogScore - An Online Evaluation Playground For Cognitive Architectures With Developmental Robotics. This work aims to present a general framework for the automated evaluation of different levels of diverse cognitive capabilities of cognitive architectures.

dynamic-neural-field-degeneration is a framework designed to simulate and study the effects of artificial neural degeneration on Dynamic Neural Field (DNF) models. This work explores the resilience and adaptability of DNFs, specifically in the context of cognitive behavior in robotic systems.

This repository contains the implementation, data-generation pipelines, and trained behavior-cloning models for a kitchen pick-and-place task using IsaacLab. Task: a Franka Emika manipulator picks a tomato soup can (container) from inside a fridge and places it inside the microwave cavity.

Reinforcement Learning in the Lego Mindstorms NXT Robot

Implementation of causal experiments

This repository composes the modules available for an attentional system based on the selection model for perception proposed by Colombini (2016). The modules were implemented with CST.

Cognibot explores how robots can achieve more natural behavior by unifying perception and action—the same neural codes that help you see a door handle also prepare your hand to reach for it. Can we build robots that work the same way?

Behavioural and Cognitive Robotics

No description provided.

Code for the DeCIFER project, implementing a robotic collaborative intelligence through intention reading and trust estimation.

Learning To Plan Tasks with Generalizable and Rapid Physical Reasoning for Embodied Manipulation