DiSECt: A Differentiable Simulator for Parameter Inference and Control in Robotic Cutting

  title={DiSECt: A Differentiable Simulator for Parameter Inference and Control in Robotic Cutting},
  author={Eric Heiden and Miles Macklin and Yashraj S. Narang and Dieter Fox and Animesh Garg and Fabio Ramos},
Robotic cutting of soft materials is critical for applications such as food processing, household automation, and surgical manipulation. As in other areas of robotics, simulators can facilitate controller verification, policy learning, and dataset generation. Moreover, differentiable simulators can enable gradient-based optimization, which is invaluable for calibrating simulation parameters and optimizing controllers. In this work, we present DiSECt: the first differentiable simulator for… 

DefGraspNets: Grasp Planning on 3D Fields with Graph Neural Nets

This work designs DefGraspNets to align with real-world grasp planning practices and enables fast gradient-based grasp optimization over 3D stress and deformation metrics, and designs a predictive graph neural network (GNN) to act as the differentiable model.

Learning Visuo-Haptic Skewering Strategies for Robot-Assisted Feeding

This work proposes a zero-shot framework to sense visuo-haptic properties of a previously unseen item and reactively skewer it, all within a single interaction, and demonstrates that this multimodal policy outperforms baselines which do not exploit both visual and haptic cues or do not reactively plan.

DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cutting

DiSECt: the first differentiable simulator for cutting soft materials is presented, which can be calibrated to match resultant forces and deformation fields from a state-of-the-art commercial solver and real-world cutting datasets, with generality across cutting velocities and object instances.

ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics

A real-time, differentiable hybrid Lagrangian-Eulerian physical simulator for deformable objects, ChainQueen, based on the Moving Least Squares Material Point Method (MLS-MPM), which can simulate deformable Objects with collisions and can be seamlessly incorporated into soft robotic systems.

ADD: Analytically Differentiable Dynamics for Multi-Body Systems with Frictional Contact

A differentiable dynamics solver that is able to handle frictional contact for rigid and deformable objects within a unified framework and enables gradient-based optimization with adaptive trade-offs between simulation accuracy and smoothness of objective function landscapes is presented.

NeuralSim: Augmenting Differentiable Simulators with Neural Networks

Through extensive experiments, the ability of the hybrid simulator to learn complex dynamics involving frictional contacts from real data, as well as match known models of viscous friction, is demonstrated, and an approach for automatically discovering useful augmentations is presented.

Simultaneous Trajectory Optimization and Force Control with Soft Contact Mechanics

A high-level framework for simultaneous trajectory optimization and force control of the interaction between manipulator and soft environments and has the potential to be leveraged for medical tasks involving manipulation of compliant, delicate, and deformable tissues is presented.

Sim-to-Real for Robotic Tactile Sensing via Physics-Based Simulation and Learned Latent Projections

This work develops an efficient, freely-accessible FEM model of the BioTac and comprises one of the first efforts to combine self-supervision, cross-modal transfer, and sim-to-real transfer for tactile sensors.

Analytical Derivatives of Rigid Body Dynamics Algorithms

This paper introduces a new algorithm to compute the inverse of the joint-space inertia matrix, without explicitly computing the matrix itself, which is implemented in the open-source C++ framework called Pinocchio.

Data-Driven Model Predictive Control for the Contact-Rich Task of Food Cutting

This paper presents a data-driven control approach that employs a recurrent neural network to model the dynamics for a Model Predictive Controller and investigates the behavior of the system during force-critical instances of cutting and illustrates its adaptive behavior in difficult cases.

A User's Guide to Calibrating Robotics Simulators

This paper proposes a set of benchmarks and a framework for the study of various algorithms aimed to transfer models and policies learnt in simulation to the real world and conducts experiments on a wide range of well known simulated environments to characterize and offer insights into the performance of different algorithms.

Robotic Cutting of Solids Based on Fracture Mechanics and FEM

This work represents the object as evenly spaced slices normal to the cutting plane such that cutting of each slice requires only a 2D mesh, and Fracture and force can be then interpolated between every two adjacent slices.