Active object reconstruction using autonomous robots is gaining great interest. A primary goal in this task is to maximize the information of the object to be reconstructed, given limited on-board resources. Previous view planning methods exhibit inefficiency since they rely on an iterative paradigm based on explicit representations, consisting of (1) planning a path to the next-best view only; and (2) requiring a considerable number of less-gain views in terms of surface coverage. To address these limitations, we propose to integrate implicit representations into the One-Shot View Planning (OSVP). The key idea behind our approach is to use implicit representations to obtain the small missing surface areas instead of observing them with extra views. Therefore, we design a deep neural network, named OSVP, to directly predict a set of views given a dense point cloud refined from an initial sparse observation. To train our OSVP network, we generate supervision labels using dense point clouds refined by implicit representations and set covering optimization problems. Simulated experiments show that our method achieves sufficient reconstruction quality, outperforming several baselines under limited view and movement budgets. We further demonstrate the applicability of our approach in a real-world object reconstruction scenario.
Batch Informed Trees (BIT*): Sampling-based Optimal Planning via the Heuristically Guided Search of Implicit Random Geometric Graphs
Carnegie Mellon University(卡内基梅隆大学);Canadian Space Agency(加拿大航天局);Defence Research and Development Canada(加拿大国防研究与发展部);Massachusetts Institute of Technology(麻省理工学院);National Aeronautics and Space Administration(美国国家航空航天局);Northern Centre for Advanced Technology Inc.(北方先进技术中心公司);Ontario Drive and Gear Ltd.(安大略传动与齿轮有限公司);Office of Naval Research(美国海军研究办公室);University of Toronto(多伦多大学);University of Waterloo(滑铁卢大学);University of Toronto Institute for Aerospace Studies(多伦多大学航空航天研究所)
DM-OSVP++: One-Shot View Planning Using 3D Diffusion Models for Active RGB-Based Object Reconstruction
University of Bonn(波恩大学);Center for Robotics(机器人中心);Lamarr Institute for Machine Learning and Artificial Intelligence(拉马尔机器学习与人工智能研究所);Delft University of Technology(代尔夫特理工大学)
Using Implicit Behavior Cloning and Dynamic Movement Primitive to Facilitate Reinforcement Learning for Robot Motion Planning
Eindhoven University of Technology(埃因霍温理工大学);University of Victoria(维多利亚大学);Natural Sciences and Engineering Research Council (NSERC) Canada(加拿大自然科学与工程研究委员会)
Explicit-Implicit Subgoal Planning for Long-Horizon Tasks with Sparse Reward
The Hong Kong Polytechnic University (PolyU)(香港理工大学);The University of Hong Kong (HKU)(香港大学);Ningbo Institute of Digital Twin, Eastern Institute of Technology (EIT)(东方理工大学宁波数字孪生研究院);University of Liverpool(利物浦大学)
STAIR: Semantic-Targeted Active Implicit Reconstruction
Institute of Geodesy and Geoinformation, University of Bonn(波恩大学大地测量与地理信息研究所);Lamarr Institute for Machine Learning and Artificial Intelligence(拉马尔机器学习与人工智能研究所)
GaLa: Hypergraph-Guided Visual Language Models for Procedural Planning
Harbin Institute of Technology(哈尔滨工业大学);Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)(广东人工智能与数字经济实验室(深圳));Chongqing Research Institute of HIT(重庆哈尔滨工业大学研究院)
Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation
Khoury College of Computer Sciences, Northeastern University(东北大学Khoury计算机科学学院);Institute for Interdisciplinary Information Sciences, Tsinghua University(清华大学交叉信息研究院);Shanghai Qi Zhi Institute(上海期智研究院)
Implicit Articulated Robot Morphology Modeling with Configuration Space Neural Signed Distance Functions
École Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院);Chalmers University of Technology(查尔姆斯理工大学);University College London(伦敦大学学院);Rice University(莱斯大学);Massachusetts Institute of Technology(麻省理工学院)
Stereo-Planner: Learning Stereo-to-Trajectory Planning for Zero-Shot Sim-to-Real Quadrotor Navigation
School of Electrical and Electronic Engineering, Nanyang Technological University(南洋理工大学电气与电子工程学院);School of Electrical and Information Engineering, Tianjin University(天津大学电气与信息工程学院)
Neural Navigation Functions for Zero-Shot Generalizable Motion Planning
University of Pennsylvania, United States(宾夕法尼亚大学,美国);Department of Mechanical Engineering and Applied Mechanics(机械工程与应用力学系);Department of Electrical and Systems Engineering(电气与系统工程系)
Socratic Planner: Self-QA-Based Zero-Shot Planning for Embodied Instruction Following
Seoul National University(首尔大学);Interdisciplinary Program in AI (IPAI), Seoul National University(首尔大学人工智能交叉项目);AI Institute, Seoul National University(首尔大学人工智能研究院)
Knowing When to Ask: Resolving Uncertainty in Human-Robot Joint Planning via Explicit Dialogue and Implicit Intent Cues
Department of Electrical and Computer Engineering, George Washington University(电气与计算机工程系,乔治华盛顿大学);Department of Mechanical and Aerospace Engineering, George Washington University(机械与航空航天工程系,乔治华盛顿大学);Department of Electrical and Computer Engineering, Northeastern University(电气与计算机工程系,东北大学)