While robots can learn models to solve many manipulation tasks from raw visual input, they cannot usually use these models to solve new problems. On the other hand, symbolic planning methods such as STRIPS have long been able to solve new problems given only a domain definition and a symbolic goal, but these approaches often struggle on the real world robotic tasks due to the challenges of grounding these symbols from sensor data in a partially-observable world. We propose Deep Planning Domain Learning (DPDL), an approach that combines the strengths of both methods to learn a hierarchical model. DPDL learns a high-level model which predicts values for a large set of logical predicates consisting of the current symbolic world state, and separately learns a low-level policy which translates symbolic operators into executable actions on the robot. This allows us to perform complex, multi-step tasks even when the robot has not been explicitly trained on them. We show our method on manipulation tasks in a photorealistic kitchen scenario.
Learning Transferable Motor Skills for Geometry-Aware Robotic Surface Tasks
Czech Institute of Informatics, Robotics, and Cybernetics（捷克信息学、机器人学与自动化研究所）；Czech Technical University in Prague（布拉格捷克技术大学）；Delft University of Technology（代尔夫特理工大学）
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；Carnegie Mellon University（卡内基梅隆大学）；Georgia Institute of Technology（佐治亚理工学院）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Simmons University（西蒙斯大学）
We introduce an algorithm for model-based hierarchical reinforcement learning to acquire self-contained transition and reward models suitable for probabilistic planning at multiple levels of abstraction. We call this framework Planning with Abstract Learned Models (PALM). By representing subtasks symbolically using a new formal structure, the lifted abstract Markov decision process (L-AMDP), PALM learns models that are independent and modular. Through our experiments, we show how PALM integrates planning and execution, facilitating a rapid and efficient learning of abstract, hierarchical model…
HuBE: Cross-Embodiment Human-like Behavior Execution for Humanoid Robots
Department of Mechanical Engineering, The Hong Kong Polytechnic University (PolyU)（机械工程系，香港理工大学（PolyU））；Research Institute for Smart Ageing (RISA), PolyU（智能老龄化研究所以及PolyU）；Ningbo Institute of Digital Twin, Eastern Institute of Technology (EIT)（宁波数字孪生研究所，东部技术研究所（EIT））
ContactGuard: Pre-Contact Execution Monitoring with Action-Conditioned Latent World Models
College of Connected Computing, Vanderbilt University（范德堡大学连接计算学院）；School of Computer Science, The University of Sydney（悉尼大学计算机学院）；Australian Centre for Robotics, The University of Sydney（悉尼大学澳大利亚机器人中心）
SAGE: Scene Graph-Aware Guidance and Execution for Long-Horizon Manipulation Tasks
School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院）；ShanghaiTech University（上海科技大学）；University of Sussex（Sussex大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
From Language to Motion: Task-Conditioned Focal-Stack Trajectory Integration for Microscopic Robots
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Zhejiang Gongshang University（浙江工商大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Toronto（多伦多大学）
From Pixels to Concepts: Growing Rich 3D Semantic Scene Graph Forests utilizing Foundation Models
FZI Research Center for Information Technology（FZI信息技术研究中心）；Machine Intelligence and Robotics Lab (MaiRo), Karlsruhe Institute for Technology (KIT)（卡尔斯鲁厄理工学院机器智能与机器人实验室）
