Object Rearrangement Using Learned Implicit Collision Functions
Explore this paper's citation graph
- Type
- preprint
- Published
- 2020-11-21
- Cited by
- 94
- References
- 56
- Access
- Open access
- OpenAlex
- https://openalex.org/W3108425990
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:227126978
Keywords
Collision, Leverage (statistics), Computer science, Object (grammar), Point cloud
References
- FCL: A general purpose library for collision and proximity queries
- GPU-based parallel collision detection for fast motion planning
- Approximating polyhedra with spheres for time-critical collision detection
- Automatic reconstruction of surfaces and scalar fields from 3D scans
- Three-dimensional alpha shapes
- Sampling and reconstruction with adaptive meshes
- Point Cloud Collision Detection
- A fast procedure for computing the distance between complex objects in three-dimensional space
- TRAC-IK: An open-source library for improved solving of generic inverse kinematics
- Marching cubes: A high resolution 3D surface construction algorithm
- Fast probabilistic collision checking for sampling-based motion planning using locality-sensitive hashing
- A Survey of Surface Reconstruction from Point Clouds
- Rearrangement planning using object-centric and robot-centric action spaces
- Semantic Scene Completion from a Single Depth Image
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- Model Predictive Path Integral Control: From Theory to Parallel Computation
- PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
- Collision Detection for Point Cloud Models With Bounding Spheres Hierarchies
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
- A Papier-Mache Approach to Learning 3D Surface Generation
Cited by
- Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes
- NeRP: Neural Rearrangement Planning for Unknown Objects
- Graph-based Cluttered Scene Generation and Interactive Exploration using Deep Reinforcement Learning
- Efficient Object Manipulation to an Arbitrary Goal Pose: Learning-Based Anytime Prioritized Planning
- Semantically Grounded Object Matching for Robust Robotic Scene Rearrangement
- Object Manipulation via Visual Target Localization
- Coarse-to-Fine Q-attention with Learned Path Ranking
- Hierarchical policy with deep-reinforcement learning for nonprehensile multiobject rearrangement
- Volumetric-based Contact Point Detection for 7-DoF Grasping
- Motion Policy Networks
- TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulation
- SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields
- Smart Explorer: Recognizing Objects in Dense Clutter via Interactive Exploration
- Closed-Loop Next-Best-View Planning for Target-Driven Grasping
- Local and Global Search-Based Planning for Object Rearrangement in Clutter
- Neural Joint Space Implicit Signed Distance Functions for Reactive Robot Manipulator Control
- IFOR: Iterative Flow Minimization for Robotic Object Rearrangement
- Local object crop collision network for efficient simulation of non-convex objects in GPU-based simulators
- Motion Planning (In)feasibility Detection using a Prior Roadmap via Path and Cut Search
- CollisionGP: Gaussian Process-Based Collision Checking for Robot Motion Planning
Related papers
- X-Ray: Mechanical Search for an Occluded Object by Minimizing Support of Learned Occupancy Distributions
- Building 3D Object Models during Manipulation by Reconstruction-Aware Trajectory Optimization
- GPR: Grasp Pose Refinement Network for Cluttered Scenes
- Monte-Carlo Tree Search for Efficient Visually Guided Rearrangement Planning
- Scene Flow from Point Clouds with or without Learning