Robot Interaction Behavior Generation based on Social Motion Forecasting for Human-Robot Interaction

2024-02-07 · Esteve Valls Mascaro, Yashuai Yan, Dongheui Lee

Integrating robots into populated environments is a complex challenge that requires an understanding of human social dynamics. In this work, we propose to model social motion forecasting in a shared human-robot representation space, which facilitates us to synthesize robot motions that interact with humans in social scenarios despite not observing any robot in the motion training. We develop a transformer-based architecture called ECHO, which operates in the aforementioned shared space to predict the future motions of the agents encountered in social scenarios. Contrary to prior works, we reformulate the social motion problem as the refinement of the predicted individual motions based on the surrounding agents, which facilitates the training while allowing for single-motion forecasting when only one human is in the scene. We evaluate our model in multi-person and human-robot motion forecasting tasks and obtain state-of-the-art performance by a large margin while being efficient and performing in real-time. Additionally, our qualitative results showcase the effectiveness of our approach in generating human-robot interaction behaviors that can be controlled via text commands. Webpage: https://evm7.github.io/ECHO/

📄 PDF Abstract BibTeX arXiv:2402.04768

Code (0)

등록된 구현이 없습니다.

Tasks

Motion Forecasting

Safe, Fluent and Acceptable Motion Generation and Execution for Human--Robot Interaction in Manufacturing Environments

2026-06-07 · Thibaut Lopez, Olivier Aycard, Pierre-Brice Wieber, Mohamed Boua 외 arxiv

Robots operating in human environments must not only ensure physical safety but also exhibit behaviors that are understandable, fluent, and acceptable to human partners. This paper investigates motion generation strategi…

The Robot's Inner Critic: Self-Refinement of Social Behaviors through VLM-based Replanning

2026-03-20 · Jiyu Lim, Youngwoo Yoon, Kwanghyun Park arxiv

Conventional robot social behavior generation has been limited in flexibility and autonomy, relying on predefined motions or human feedback. This study proposes CRISP (Critique-and-Replan for Interactive Social Presence)…

Awakening Facial Emotional Expressions in Human-Robot

2025-10-27 · Yongtong Zhu, Lei Li, Iggy Qian, WenBin Zhou 외 arxiv

The facial expression generation capability of humanoid social robots is critical for achieving natural and human-like interactions, playing a vital role in enhancing the fluidity of human-robot interactions and the accu…

A MultiModal Social Robot Toward Personalized Emotion Interaction

2021-10-08 · Baijun Xie, Chung Hyuk Park

Human emotions are expressed through multiple modalities, including verbal and non-verbal information. Moreover, the affective states of human users can be the indicator for the level of engagement and successful interac…

reinforcement-learning Reinforcement Learning (RL)

Learning Socially Appropriate Robot Approaching Behavior Toward Groups using Deep Reinforcement Learning

2018-10-16 · Yuan Gao, Fangkai Yang, Martin Frisk, Daniel Hernandez 외

Deep reinforcement learning has recently been widely applied in robotics to study tasks such as locomotion and grasping, but its application to social human-robot interaction (HRI) remains a challenge. In this paper, we …

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)