SLAI Seminar 30th Session will be discussing the topic on "Towards embodied multi-intelligences: how far are we? ",  from 2:30pm-4pm, March 19th (Thursday) at Room B401, online participation is welcome.

 (Tencent Meeting ID: 182-510-928)

报告主题：迈向具身多元智能：我们离目标还有多远？

时间：2026年3月19日（周四）下午2:30-4:00

地点: 深圳河套学院B401教室

线上参与：腾讯会议号182-510-928

主讲嘉宾：Gordon Cheng教授

主持人：李海洲教授

讲者简介About the Speaker:

Gordon Cheng教授是人形机器人、神经工程与人工智能领域的权威专家，二十余年来为这些领域做出了开创性贡献。自2010年起，他担任德国慕尼黑工业大学认知系统首席教授及认知系统研究所所长。除学术职务外，他还创立了三家分别专注于物流、高性能执行器和机器人技术的初创公司。其最新企业intouch-robotics致力于将人造敏感皮肤研究成果应用于全工业领域的各类机器人。此外，他主持着极具声望的精英硕士项目——神经工程理学硕士（MSNE），该项目隶属于巴伐利亚精英网络。同时，他负责管理神经工程能力中心，彰显了其推动关键领域研究与教育的坚定决心。

Cheng教授是20项专利的联合发明人，合著超过450篇技术出版物，涵盖会议论文、评论文章、专著及专著章节。其突破性的跨学科研究为他赢得了众多奖项与荣誉，包括2017年因其对人形机器人系统及神经机器人学的卓越贡献而当选IEEE会士。2024年，他因在机器人科学与技术领域的杰出成就荣获日本机器人学会会士称号，实至名归。此外，他于2023年获得备受瞩目的欧洲研究理事会（ERC）高级资助项目，用于开发创新性的“旨在恢复自主行走能力的软体外骨骼套装”（STROLL）。Cheng教授研究兴趣广泛且影响深远，涵盖神经机器人学、人形机器人、模仿学习、认知系统、人工智能及神经工程等多个领域。

Professor Gordon Cheng is a prominent expert in humanoid robotics, neuroengineering, and artificial intelligence, with over two decades of groundbreaking contributions to these fields. Since 2010, he has served as the Chair Professor for Cognitive Systems and is the Director of the Institute for Cognitive Systems at the Technical University of Munich, Germany. In addition to his academic roles, Cheng has founded three startups spanning logistics, high-performance actuators, and robotics. His latest venture, intouch-robotics, aims to apply his research on artificial sensitive skin to all robots across all industrial domains. In addition, he directs the prestigious Elite Master of Science in Neuroengineering (MSNE), a highly selective program within the Elite Network of Bavaria (ENB). Additionally, he oversees the Centre of Competence in Neuroengineering, underscoring his dedication to advancing research and education in these critical areas.Gordon Cheng is an accomplished co-inventor of 20 patents and has co-authored over 450 technical publications, including conference proceedings, editorials, books, and book chapters. His groundbreaking interdisciplinary work earned him numerous prizes and awards, including the prestigious IEEE Fellowship in 2017, recognizing his significant contributions to humanoid robotic systems and neurorobotics. In 2024, he was rightfully honored with the RSJ Fellowship for his outstanding achievements in robotics science and technology. Furthermore, he secured the esteemed European Research Council (ERC) Advanced Grant in 2023 to develop an innovative “soft exoskeleton suit designed to restore autonomous locomotion” (STROLL). His research interests are diverse and impactful, encompassing neuro-robotics, humanoid robotics, imitation learning, cognitive systems, artificial intelligence, and neuroengineering.

报告摘要：

本次报告，Cheng教授将探讨多年来持续研究的具身智能的多个层面，并通过若干案例研究进行阐述。这些案例将涵盖从形态学方法到感知运动学习，再到认知推理等多个维度。尽管实例展示了特定形式具身智能的成功实践，但Cheng教授希望提出一个关键问题：我们能否继续沿用当前将智能割裂为封闭、单一形态的方法来制造智能机器？还是需要全新的方法论，或者说对具身智能的认知范式需要进行根本性转变？

首先, Cheng教授将聚焦机器人的触觉智能。人类终其一生都依赖触觉这种多维能力——它既赋予我们对世界的感知，又塑造着日常体验。随着机器人全身触觉感知技术的重大突破，我们正构建起超越传统机器人能力的"触觉智能体系"。这项进步使机器人不仅能感知环境，更能以类人方式进行物理交互。Cheng教授将通过多个应用实例展示其发展：包括人形机器人的全身交互、人机协作、人形机器人运动性能优化、可移动障碍环境中的机器人导航、双足外骨骼的运动控制，以及多机器人协同作业。

然而，要完全实现机器人的智能仍有诸多挑战亟待突破。因此机器人通过观察进行学习的机制将被重点阐述。人类示范学习是提升人类与机器人能力的最有效途径之一，Cheng教授将展示三种人机示范学习方法：直接模仿、目标选择与目的性学习——这些方法有望将物理人工智能推向新高度。通过多个真实场景的应用案例，详细阐释这些学习机制的具体实现方式。

Abstract:

In this talk, I will discuss various aspects of embodied intelligence that I have been exploring over the years and present several case studies. These will range from morphological approaches to sensory-motor learning and cognitive reasoning. While many of these cases showcase successful examples of specialized forms of embodied intelligence, I want to raise an important question: Can we continue to engineer intelligent machines using our current methods, which compartmentalize intelligence into closed, singular forms? Or do we need a new methodology or a fundamental paradigm shift in how we think about embodied intelligence?First, I will examine tactile intelligence in robots. Throughout our lives, we rely on our sense of touch, a versatile ability that provides awareness of the world and shapes our daily experiences. Significant advancements in whole-body tactile sensing for robots have led to the development of what we call “tactile intelligence,” which extends beyond the traditional capabilities of robotic systems. This advancement allows robots to sense their environment and physically interact with it in ways that resemble human behavior. I will share several examples of its applications, including whole-body interaction with humanoid robots, human-robot interaction, improved locomotion for humanoid robots, robot navigation among movable objects, locomotion control for bipedal exoskeletons, and robot collaboration.Furthermore, there are still considerable challenges to overcome to fully realize intelligence in robotics. Thus, I will present aspects of robot learning from others. Learning from human demonstrations is one of the most powerful mechanisms for enhancing capabilities in both humans and robots. Here, I show three methods for human and robot learning from demonstrations: direct mimicry, goal selection, and purposive learning, which I believe will take Physical AI to new heights. I will illustrate aspects of these mechanisms through several real-world examples.