Human-Robot Interaction Using Affective Cues
PulseAugur coverage of Human-Robot Interaction Using Affective Cues — every cluster mentioning Human-Robot Interaction Using Affective Cues across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
New method improves robot learning from human feedback
A new research paper proposes IMPLIED, a method for improving preference learning in human-robot collaboration. Traditional methods rely on fixed rules to infer human preferences, but this paper shows that human-provide…
-
Robots infer human goals by guiding them to critical decision points
Researchers have developed a novel strategy to enable robots to infer human goals more accurately and earlier during interactions. This approach focuses on guiding humans toward "Critical Decision Points" (CDPs), which …
-
New SocioGesture System Enhances Real-Time Social Gesture Perception for Robots
Researchers have developed SocioGesture, a novel system designed for real-time social gesture recognition in human-robot interaction (HRI). This system utilizes a lightweight, dual-stream model that fuses body motion wi…
-
New ontology aims to resolve contradictions in human-robot dialogue
Researchers are developing a foundational ontology, named ATFOt (Activity Theory-based foundational ontology), to formally represent and identify contradictions within dialogue-based human-robot interactions. This ontol…
-
New framework guides LLM prompting for grounded robot personas
A new research paper proposes a framework for designing prompts for large language models (LLMs) used in social robots. The framework aims to address issues like hallucinated capabilities and unclear behavioral boundari…
-
PoseOFF improves human action anticipation for robots · 2 sources tracked
Researchers have developed PoseOFF, a novel pose-anchored optical flow representation designed to improve human action anticipation in human-robot interaction. This method captures localized motion around human joints, …
-
New framework trains robots for embodied cognition using synthetic worlds
Researchers have developed a conceptual framework for training Vision-Language Models (VLMs) to enhance embodied cognition in robots, specifically focusing on Visual Perspective Taking (VPT). To facilitate this, they ge…
-
VR and VLMs enhance robot situational awareness in hazardous settings
Researchers have developed a virtual reality (VR) framework to study how robots equipped with vision-language models (VLMs) can improve situational awareness in dangerous environments. The system allows a robot to explo…
-
LLMs enable robots to synthesize actions from speech, gestures, and music
Researchers have developed a new framework that uses Large Language Models (LLMs) to enable robots to synthesize actions from multimodal human inputs. This system integrates speech recognition, gesture analysis, and mus…
-
New Transformer Model Predicts Long-Term Human Motion with Occlusion Recovery
Researchers have developed a novel non-autoregressive transformer model for predicting human motion over extended periods. This model addresses limitations of existing autoregressive methods by focusing on both local po…
-
Small Language Models Augment Human Reviewers in Tracking Robotics Research
Researchers have developed a systematic review pipeline to track the rapid growth in social-physical human-robot interaction (spHRI). This pipeline utilizes small language models (SLMs) to assist human reviewers in scre…
-
Robot Pepper learns expressive gestures using ChatGPT and RLHF
Researchers have developed a novel method for generating natural and expressive gestures for the humanoid robot Pepper by integrating ChatGPT and Reinforcement Learning with Human Feedback (RLHF). Initial attempts using…
-
New PATCH system enhances robot manipulation stability
Researchers have developed PATCH, a novel system for monitoring robot manipulation tasks in real-world environments. This action-chunk-conditioned latent patch innovation monitor aims to improve the robustness of learni…
-
Robot interaction framework uses vision and speech for intent
Researchers have developed a new framework called EDITH that integrates verbal and nonverbal human signals for more natural human-robot interaction. This system captures first-person video, gaze, and speech from smart g…