Social Robotics

Overview

As robots become more and more ubiquitous in our everyday lives, it becomes essential to study their behaviour in real-world social environments. Robots placed in human-centred environments need to make decisions that conform to social notions effortlessly in a flexible manner. They need to learn to navigate and interact with humans in a 'socially-aware manner'. Humans need to feel safe enough to trust robot actions in everyday environments. In a similar manner, a robot dependent on human assistance also needs to identify if the guidance given to it is trustworthy. A mutual understanding between the two is critical in human-robot interaction scenarios. Research in social robotics deals with developing algorithms towards achieving these goals.

Can a robot trust you? - A DRL approach to Social Robot Navigation:

This work explores the idea of human-robot trust from a robot’s perspective, rather than from a human standpoint. It raises the question as to whether a robot can trust humans on the guidance they give it when placed in an unknown environment. In order to answer this, a deep reinforcement learning approach is presented, in which an optimal navigation policy is learnt via a social reward.

 

Paper - Can a Robot Trust You? A DRL-Based Approach to Trust-Driven Human-Guided Navigation - Vishnu Sashank Dorbala, Arjun Srinivasan, Aniket Bera

Code - https://github.com/vdorbala/DRL-Robot-Trust

Proxemo - Emotion Learning for Socially Aware Navigation:

In this work, we present a deep learning approach for deciphering emotions from gaits. The extracted emotions along with psychology obtained proxemic constraints are used to navigate the robot in a socially aware manner. The results showcase a significant improvement in the accuracy of emotion prediction from gait sequences, which in turn improves the overall performance of the navigation scheme.

 

Paper - ProxEmo: Gait-based Emotion Learning and Multi-view Proxemic Fusion for Socially-Aware Robot Navigation - Venkatraman Narayanan, Bala Murali Manoghar, Vishnu Sashank Dorbala, Dinesh Manocha, Aniket Bera

Code - https://github.com/vijay4313/proxemo

Publications

Project Conference/Journal Year
Can a robot trust you? - A DRL approach to Social Robot Navigation ICRA 2021
ProxEmo: Gait-based Emotion Learning and Multi-view Proxemic Fusion for Socially-Aware Robot Navigation IROS 2020
How are you feeling? Multimodal Emotion Learning for Socially-Assistive Robot Navigation IEEE FG 2020
EWareNet: Emotion Aware Human Intent Prediction and Adaptive Spatial Profile Fusion for Social Robot Navigation arXiv 2020
SeekNet: Improved Human Instance Segmentation via Reinforcement Learning Based Optimized Robot Relocation arXiv 2020