mlsanityData to 7 Oct 2026

An End-to-End Differentiable Framework for Contact-Aware Robot Design

arXiv 2107.07501 ↗First posted 15 Jul 2021cs.RO cs.AI cs.GRcited by 53

Not on the map. Why?

Abstract (arXiv)

The current dominant paradigm for robotic manipulation involves two separate stages: manipulator design and control. Because the robot's morphology and how it can be controlled are intimately linked, joint optimization of design and control can significantly improve performance. Existing methods for co-optimization are limited and fail to explore a rich space of designs. The primary reason is the trade-off between the complexity of designs that is necessary for contact-rich tasks against the practical constraints of manufacturing, optimization, contact handling, etc. We overcome several of these challenges by building an end-to-end differentiable framework for contact-aware robot design. The two key components of this framework are: a novel deformation-based parameterization that allows for the design of articulated rigid robots with arbitrary, complex geometry, and a differentiable rigid body simulator that can handle contact-rich scenarios and computes analytical gradients for a full spectrum of kinematic and dynamic parameters. On multiple manipulation tasks, our framework outperforms existing methods that either only optimize for control or for design using alternate representations or co-optimize using gradient-free methods.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Builds on 24 of its 55 references that are in the map. First posted on arXiv 15 Jul 2021.

Builds on

24 of 55 references.

References · 24

  1. 2019Solving Rubik's Cube with a Robot Handcited by 699
  2. 2018Learning Dexterous In-Hand Manipulationcited by 643
  3. 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 588
  4. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  5. 2019DiffTaichi: Differentiable Programming for Physical Simulationcited by 248
  6. 2018Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluidscited by 219
  7. 2019Deep Dynamics Models for Learning Dexterous Manipulationcited by 200
  8. 2021Embodied Intelligence via Learning and Evolutioncited by 154
  9. 2016A Compositional Object-Based Approach to Learning Physical Dynamicscited by 119
  10. 2016A Differentiable Physics Engine for Deep Learning in Roboticscited by 107
  11. 2021gradSim: Differentiable simulation for system identification and visuomotor controlcited by 100
  12. 2021PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physicscited by 100
12 more
  1. 2018ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Roboticscited by 98
  2. 2018Flexible Neural Representation for Physics Predictioncited by 91
  3. 2020Scalable Differentiable Physics for Learning and Controlcited by 72
  4. 2018Jointly Learning to Construct and Control Agents using Deep Reinforcement Learningcited by 51
  5. 2019Neural Graph Evolution: Towards Efficient Automatic Robot Designcited by 34
  6. 2019Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learningcited by 34
  7. 2020Hardware as Policy: Mechanical and Computational Co-Optimization using Deep Reinforcement Learningcited by 29
  8. 2020Fit2Form: 3D Generative Model for Robot Gripper Form Designcited by 21
  9. 2021Multi-Objective Graph Heuristic Search for Terrestrial Robot Designcited by 18
  10. 2019Interactive Differentiable Simulationcited by 17
  11. 2020Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objectscited by 11
  12. 2017Functional Co-Optimization of Articulated Robotscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 8; 2023: 11; 2024: 9; 2025: 17; 2026: 7.

53 papers.

Sort:

By area:

  1. 2022Accelerated Policy Learning with Parallel Differentiable Simulationcited by 92
  2. 2022Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapescited by 92
  3. 2022Physical Design using Differentiable Learned Simulatorscited by 37
  4. 2023FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulationcited by 37
  5. 2022RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimationcited by 29
  6. 2023Physics-Informed Machine Learning for Modeling and Control of Dynamical Systemscited by 28
  7. 2025Dress-1-to-3: Single Image to Simulation-Ready 3D Outfit with Diffusion Prior and Differentiable Physicscited by 19
  8. 2024Adaptive Horizon Actor-Critic for Policy Learning in Contact-Rich Differentiable Simulationcited by 18
  9. 2023ASAP: Automated Sequence Planning for Complex Robotic Assembly with Physical Feasibilitycited by 17
  10. 2024QuasiSim: Parameterized Quasi-Physical Simulators for Dexterous Manipulations Transfercited by 10
  11. 2022Learning Tool Morphology for Contact-Rich Manipulation Tasks with Differentiable Simulationcited by 9
  12. 2025VLMgineer: Vision Language Models as Robotic Toolsmithscited by 9
38 more
  1. 2023MORPH: Design Co-optimization with Reinforcement Learning via a Differentiable Hardware Model Proxycited by 8
  2. 2024Text2Robot: Evolutionary Robot Design from Text Descriptionscited by 8
  3. 2023Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithmscited by 7
  4. 2024Dynamics-Guided Diffusion Model for Sensor-less Robot Manipulator Designcited by 7
  5. 2025Neural Robot Dynamicscited by 7
  6. 2025CoReVLA: A Dual-Stage End-to-End Autonomous Driving Framework for Long-Tail Scenarios via Collect-and-Refinecited by 7
  7. 2022Differentiable Physics Simulations with Contacts: Do They Have Correct Gradients w.r.t. Position, Velocity and Control?cited by 6
  8. 2023Local object crop collision network for efficient simulation of non-convex objects in GPU-based simulatorscited by 5
  9. 2023Improving Gradient Computation for Differentiable Physics Simulation with Contactscited by 5
  10. 2024One-Shot Real-to-Sim via End-to-End Differentiable Simulation and Renderingcited by 5
  11. 2025JAX-MPM: A Learning-Augmented Differentiable Meshfree Framework for GPU-Accelerated Lagrangian Simulation and Geophysical Inverse Modelingcited by 5
  12. 2023Tactile-Filter: Interactive Tactile Perception for Part Matingcited by 4
  13. 2023STAMP: Differentiable Task and Motion Planning via Stein Variational Gradient Descentcited by 4
  14. 2024Task2Morph: Differentiable Task-inspired Framework for Contact-Aware Robot Designcited by 4
  15. 2025House of Dextra: Cross-embodied Co-design for Dexterous Handscited by 4
  16. 2025Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challengescited by 4
  17. 2021DiffSRL: Learning Dynamical State Representation for Deformable Object Manipulation with Differentiable Simulatorcited by 3
  18. 2023HandyPriors: Physically Consistent Perception of Hand-Object Interactions with Differentiable Priorscited by 3
  19. 2025MaNGO - Adaptable Graph Network Simulators via Meta-Learningcited by 3
  20. 2026Simulation-Ready Cluttered Scene Estimation via Physics-aware Joint Shape and Pose Optimizationcited by 3
  21. 2022C^2:Co-design of Robots via Concurrent Networks Coupling Online and Offline Reinforcement Learningcited by 2
  22. 2022Design of Unmanned Air Vehicles Using Transformer Surrogate Modelscited by 2
  23. 2025TopoGaussian: Inferring Internal Topology Structures from Visual Cluescited by 2
  24. 2025A Design Co-Pilot for Task-Tailored Manipulatorscited by 2
  25. 2024MeMo: Meaningful, Modular Controllers via Noise Injectioncited by 1
  26. 2024DEF-oriCORN: efficient 3D scene understanding for robust language-directed manipulation without demonstrationscited by 1
  27. 2025Unlocking Efficient Vehicle Dynamics Modeling via Analytic World Modelscited by 1
  28. 2025Accelerated Learning with Linear Temporal Logic using Differentiable Simulationcited by 1
  29. 2025Context-aware Learned Mesh-based Simulation via Trajectory-Level Meta-Learningcited by 1
  30. 2025Autonomous Vehicle Path Planning by Searching With Differentiable Simulationcited by 1
  31. 2025Neural Modular Physics for Elastic Simulationcited by 1
  32. 2026Latent Diffeomorphic Co-Design of End-Effectors for Deformable and Fragile Object Manipulationcited by 1
  33. 2026D-REX: Differentiable Real-to-Sim-to-Real Engine for Learning Dexterous Graspingcited by 1
  34. 2026Robust In-Hand Manipulation via Priors in Reinforcement Learning and Mechanical Designcited by 1
  35. 2023Latent Task-Specific Graph Network Simulatorscited by 0
  36. 2024Differentiable Quantum Computing for Large-scale Linear Controlcited by 0
  37. 2025A Modularized Design Approach for GelSight Family of Vision-based Tactile Sensorscited by 0
  38. 2025AI-Enhanced Automatic Design of Efficient Underwater Gliderscited by 0

50 most cited of 53 All 53 (JSON)