Learning Task-Oriented Grasping for Tool Manipulation from Simulated Self-Supervision
Not on the map. Why?
Abstract (arXiv)
Tool manipulation is vital for facilitating robots to complete challenging task goals. It requires reasoning about the desired effect of the task and thus properly grasping and manipulating the tool to achieve the task. Task-agnostic grasping optimizes for grasp robustness while ignoring crucial task-specific constraints. In this paper, we propose the Task-Oriented Grasping Network (TOG-Net) to jointly optimize both task-oriented grasping of a tool and the manipulation policy for that tool. The training process of the model is based on large-scale simulated self-supervision with procedurally generated tool objects. We perform both simulated and real-world experiments on two tool-based manipulation tasks: sweeping and hammering. Our model achieves overall 71.1% task success rate for sweeping and 80.0% task success rate for hammering. Supplementary material is available at: bit.ly/task-oriented-grasp
Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Jun 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 16; 2022: 4; 2023: 8; 2024: 5; 2025: 7; 2026: 10.
50 papers.
Sort:
By area:
- 2021Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenescited by 213
- 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 193
- 2022OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interactioncited by 129
- 2021Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representationscited by 107
- 2021ManipulaTHOR: A Framework for Visual Object Manipulationcited by 101
- 2021VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objectscited by 78
- 2021Semantics for Robotic Mapping, Perception and Interaction: A Surveycited by 56
- 2021CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulationcited by 49
- 2022DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Toolscited by 44
- 2023Creative Robot Tool Use with Large Language Modelscited by 42
- 2021One-Shot Object Affordance Detection in the Wildcited by 40
- 2023M2T2: Multi-Task Masked Transformer for Object-centric Pick and Placecited by 40
38 more
- 2024A Survey of Embodied Learning for Object-Centric Robotic Manipulationcited by 34
- 2025GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Trainingcited by 32
- 2022Leveraging Language for Accelerated Learning of Tool Manipulationcited by 26
- 2021Learning Visual Affordance Grounding from Demonstration Videoscited by 25
- 2021A Joint Network for Grasp Detection Conditioned on Natural Language Commandscited by 23
- 2021How to select and use tools? : Active Perception of Target Objects Using Multimodal Deep Learningcited by 15
- 2024ShapeGrasp: Zero-Shot Task-Oriented Grasping with Large Language Models through Geometric Decompositioncited by 14
- 2023FingerSLAM: Closed-loop Unknown Object Localization and Reconstruction from Visuo-tactile Feedbackcited by 12
- 2021Collision-Aware Target-Driven Object Grasping in Constrained Environmentscited by 11
- 2025VLMgineer: Vision Language Models as Robotic Toolsmithscited by 9
- 2023Learning Reusable Manipulation Strategiescited by 8
- 2023Learning to Design and Use Tools for Robotic Manipulationcited by 7
- 2021Scene Editing as Teleoperation: A Case Study in 6DoF Kit Assemblycited by 6
- 2023Learning Generalizable Tool-use Skills through Trajectory Generationcited by 6
- 2024One-Shot Manipulation Strategy Learning by Making Contact Analogiescited by 6
- 2021Discovering Generalizable Skills via Automated Generation of Diverse Taskscited by 5
- 2024MaxMI: A Maximal Mutual Information Criterion for Manipulation Concept Discoverycited by 5
- 2025Task-Oriented 6-DoF Grasp Pose Detection in Clutterscited by 4
- 2025RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skillscited by 4
- 2024Visual Imitation Learning of Task-Oriented Object Grasping and Rearrangementcited by 3
- 2025Afford-X: Generalizable and Slim Affordance Reasoning for Task-oriented Manipulationcited by 3
- 2022Fixing Malfunctional Objects With Learned Physical Simulation and Functional Predictioncited by 2
- 2023Self-Supervised Learning of Action Affordances as Interaction Modescited by 2
- 2023Learning Generalizable Tool Use with Non-rigid Grasp-pose Registrationcited by 2
- 2025Point2Act: Efficient 3D Distillation of Multimodal LLMs for Zero-Shot Context-Aware Graspingcited by 2
- 2021Text-driven object affordance for guiding grasp-type recognition in multimodal robot teachingcited by 1
- 2021Single RGB-D Camera Teleoperation for General Robotic Manipulationcited by 1
- 2026Generate, Transfer, Adapt: Learning Functional Dexterous Grasping from a Single Human Demonstrationcited by 1
- 2026Imitating What Works: Simulation-Filtered Modular Policy Learning from Human Videoscited by 1
- 2025Adaptive Inverse Kinematics Framework for Learning Variable-Length Tool Manipulation in Roboticscited by 0
- 2026Creative Robot Tool Use by Counterfactual Reasoningcited by 0
- 2026COBALT: Crowdsourcing Robot Learning via Cloud-Based Teleoperation with Smartphonescited by 0
- 2026Object Pose and Shape Estimation for Grasping: Does it Work?cited by 0
- 2026NDPP-Grasp: Non-Differentiable Physical Plausibility Constraint-Guided Task-Oriented Dexterous Grasp Generationcited by 0
- 2026GROW2: Grounding Which and Where for Robot Tool Usecited by 0
- 2026FuncBridge: Towards Functional Tool-Use Generalization via Keypoint Trajectory Reasoningcited by 0
- 2026Iterative Grasp Pose Refinement: A Deep Reinforcement Learning Approach for 2D Visioncited by 0
- 2026EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videoscited by 0
- 2026EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos30 Sep 2026
- 2026Iterative Grasp Pose Refinement: A Deep Reinforcement Learning Approach for 2D Vision18 Aug 2026
- 2026FuncBridge: Towards Functional Tool-Use Generalization via Keypoint Trajectory Reasoning7 Jul 2026
- 2026GROW2: Grounding Which and Where for Robot Tool Use29 Jun 2026
- 2026NDPP-Grasp: Non-Differentiable Physical Plausibility Constraint-Guided Task-Oriented Dexterous Grasp Generation1 Jun 2026
- 2026Object Pose and Shape Estimation for Grasping: Does it Work?26 May 2026
- 2026COBALT: Crowdsourcing Robot Learning via Cloud-Based Teleoperation with Smartphones18 May 2026
- 2026Creative Robot Tool Use by Counterfactual Reasoning6 May 2026
- 2026Imitating What Works: Simulation-Filtered Modular Policy Learning from Human Videos13 Feb 2026
- 2026Generate, Transfer, Adapt: Learning Functional Dexterous Grasping from a Single Human Demonstration8 Jan 2026
- 2025Adaptive Inverse Kinematics Framework for Learning Variable-Length Tool Manipulation in Robotics30 Oct 2025
- 2025Point2Act: Efficient 3D Distillation of Multimodal LLMs for Zero-Shot Context-Aware Grasping5 Aug 2025
38 more
- 2025GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training17 Jul 2025
- 2025VLMgineer: Vision Language Models as Robotic Toolsmiths16 Jul 2025
- 2025RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills17 Jun 2025
- 2025Afford-X: Generalizable and Slim Affordance Reasoning for Task-oriented Manipulation5 Mar 2025
- 2025Task-Oriented 6-DoF Grasp Pose Detection in Clutters24 Feb 2025
- 2024One-Shot Manipulation Strategy Learning by Making Contact Analogies14 Nov 2024
- 2024A Survey of Embodied Learning for Object-Centric Robotic Manipulation21 Aug 2024
- 2024MaxMI: A Maximal Mutual Information Criterion for Manipulation Concept Discovery21 Jul 2024
- 2024ShapeGrasp: Zero-Shot Task-Oriented Grasping with Large Language Models through Geometric Decomposition26 Mar 2024
- 2024Visual Imitation Learning of Task-Oriented Object Grasping and Rearrangement20 Mar 2024
- 2023Learning Reusable Manipulation Strategies6 Nov 2023
- 2023M2T2: Multi-Task Masked Transformer for Object-centric Pick and Place2 Nov 2023
- 2023Learning to Design and Use Tools for Robotic Manipulation1 Nov 2023
- 2023Creative Robot Tool Use with Large Language Models19 Oct 2023
- 2023Learning Generalizable Tool-use Skills through Trajectory Generation29 Sep 2023
- 2023Learning Generalizable Tool Use with Non-rigid Grasp-pose Registration31 Jul 2023
- 2023Self-Supervised Learning of Action Affordances as Interaction Modes27 May 2023
- 2023FingerSLAM: Closed-loop Unknown Object Localization and Reconstruction from Visuo-tactile Feedback14 Mar 2023
- 2022Leveraging Language for Accelerated Learning of Tool Manipulation27 Jun 2022
- 2022Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction5 May 2022
- 2022DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools31 Mar 2022
- 2022OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction29 Mar 2022
- 2021Scene Editing as Teleoperation: A Case Study in 6DoF Kit Assembly9 Oct 2021
- 2021CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulation19 Sep 2021
- 2021Learning Visual Affordance Grounding from Demonstration Videos12 Aug 2021
- 2021One-Shot Object Affordance Detection in the Wild8 Aug 2021
- 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations30 Jul 2021
- 2021VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects28 Jun 2021
- 2021Single RGB-D Camera Teleoperation for General Robotic Manipulation28 Jun 2021
- 2021Discovering Generalizable Skills via Automated Generation of Diverse Tasks26 Jun 2021
- 2021How to select and use tools? : Active Perception of Target Objects Using Multimodal Deep Learning4 Jun 2021
- 2021ManipulaTHOR: A Framework for Visual Object Manipulation22 Apr 2021
- 2021Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations4 Apr 2021
- 2021Collision-Aware Target-Driven Object Grasping in Constrained Environments1 Apr 2021
- 2021A Joint Network for Grasp Detection Conditioned on Natural Language Commands1 Apr 2021
- 2021Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes25 Mar 2021
- 2021Text-driven object affordance for guiding grasp-type recognition in multimodal robot teaching27 Feb 2021
- 2021Semantics for Robotic Mapping, Perception and Interaction: A Survey2 Jan 2021
- 2021Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenescited by 213
- 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 193
- 2022OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interactioncited by 129
- 2021Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representationscited by 107
- 2021ManipulaTHOR: A Framework for Visual Object Manipulationcited by 101
- 2021VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objectscited by 78
- 2021Semantics for Robotic Mapping, Perception and Interaction: A Surveycited by 56
- 2021CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulationcited by 49
- 2022DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Toolscited by 44
- 2021One-Shot Object Affordance Detection in the Wildcited by 40
- 2023M2T2: Multi-Task Masked Transformer for Object-centric Pick and Placecited by 40
- 2024A Survey of Embodied Learning for Object-Centric Robotic Manipulationcited by 34
12 most cited of 40 All 40 (JSON)
- 2026EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos30 Sep 2026
- 2026Iterative Grasp Pose Refinement: A Deep Reinforcement Learning Approach for 2D Vision18 Aug 2026
- 2026FuncBridge: Towards Functional Tool-Use Generalization via Keypoint Trajectory Reasoning7 Jul 2026
- 2026Object Pose and Shape Estimation for Grasping: Does it Work?26 May 2026
- 2026Imitating What Works: Simulation-Filtered Modular Policy Learning from Human Videos13 Feb 2026
- 2026Generate, Transfer, Adapt: Learning Functional Dexterous Grasping from a Single Human Demonstration8 Jan 2026
- 2025Adaptive Inverse Kinematics Framework for Learning Variable-Length Tool Manipulation in Robotics30 Oct 2025
- 2025GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training17 Jul 2025
- 2025Task-Oriented 6-DoF Grasp Pose Detection in Clutters24 Feb 2025
- 2024One-Shot Manipulation Strategy Learning by Making Contact Analogies14 Nov 2024
- 2024A Survey of Embodied Learning for Object-Centric Robotic Manipulation21 Aug 2024
- 2024MaxMI: A Maximal Mutual Information Criterion for Manipulation Concept Discovery21 Jul 2024
12 newest of 40 All 40 (JSON)