Search

The anticipation of ongoing human interactions is not only highly dynamic and challenging problem but extremely crucial in applications such as remote monitoring, video surveillance, human-robot interaction, anti-terrorists and anti-crime securities. In this work, we address the problem of anticipating the interactions between people monitored by single as well as multiple camera views. To this end, we propose a novel approach that integrates Deep Features with novel hand-crafted features, namely Transformed Optical Flow Components (TOFCs). In order to validate the performance of the proposed approach, we have tested the proposed approach in real outdoor environments, captured using single as well as multiple cameras, having shadow and illumination variations as well as cluttered backgrounds. The results of the proposed approach are also compared with the state-of-the-art approaches. The experimental results show that the proposed approach is promising to anticipate real human interactions.

This research article presents a preliminary longitudinal study to check the improvement in multi-human communication of children with Autism Spectrum Disorder (ASD) using a standardized multi-robot therapy. The research is based on a 3 step framework: 1) Human-Human Interaction, Stage-1 (HHI-S1), 2) Human-Robot Interaction, Stage-2 (HRI-S2), and 3) Human-Human Interaction, Stage-3 (HHI-S3). All three stages of the therapy consist of two command sets: 1) Controls commands and 2) Evaluation commands (auditory commands, visual commands, and combination of both). The concept of multiple robots is introduced to help multi-human communication and discourage isolation in ASD children. The joint attention of an ASD child is improved by the robotic therapy in stage 2 considering it as a key parameter for a multi-human communication scenario. The improvement in joint attention results in better command following in a triad multi-human communication scenario in stage 3 as compared to stage 1. The proposed intervention has been tested on 8 ASD subjects with 10 sessions over a period of two and a half months (10 weeks). Each session of human-human interaction (stage 1 and 3) consisted of 14 cues whereas 18 cues were presented by each robot for human-robot interaction (stage 2). The results indicate an overall 86% improvement in the social communication skills of ASD children in case of a multi-human scenario. Validation of results and effectiveness of the therapy has been further accomplished through the use of the Childhood Autism Rating Scale (CARS) score.

Learning movement primitive from unstructured demonstrations has become a popular topic in recent years, which provides a natural way to endow human-inspired skills to robots. The main idea of movement primitives is that should suffice to reconstruct a large set of complex manipulation tasks. However, conventional learning methods mostly focus on the kinesthetic variables and ignore those critical introspective capacities in manipulation such as movement generalization and assessment of the sensory signals. In this paper, we investigate the association of generalization, fault detection, fault diagnoses, and task exploration during manipulation task, and call such movement primitives augmented with introspective capacities Introspective Movement Primitives (IMP). With our previous work, this paper mainly addresses how IMPs can be acquired by assessing the quality of multimodal sensory data of unstructured demonstrations and how they can incrementally create manipulation task by reverse execution and human interaction. Experimental evaluation on a human-robot collaborative packaging task with a Rethink Baxter robot, results indicate that our proposed method can effectively increase robustness towards external perturbations and adaptive exploration during robot manipulation task.