Nvidia Corporation

Miles Macklin

Nuttapong Chentanez

Matthias Mueller-Fischer

Stefan Jeschke

Dieter Fox

Fabio Tozeto Ramos

Ankur Handa

Tucker Ryer Hermans

Yashraj Shyam Narang

Viktor Makoviichuk

Isabella Huang

Animesh Garg

Balakumar Sundaralingam

Clemens Eppner

Yevgen Chebotar

Nathan Donald Ratliff

Matthias Müller

Krishna Murthy Jatavallabhula

Tae-Yong Kim

Jan Issac

Matthias Mueller Fischer

Apparatuses, systems, and techniques to generate a predicted outcome of an object resulting from a robotic component applying a force. In at least one embodiment, a predicted outcome of an object resulting from a robotic component applying a force is generated based on, for example, a neural network.

Predicting grasp outcomes

Apparatuses, systems, and techniques to update a machine learning model associated with an object. In at least one embodiment, the machine learning model is updated based at least in part on, for example, one or more distributions associated with the machine learning model.

Predicting object models

A machine-learning control system is trained to perform a task using a simulation. The simulation is governed by parameters that, in various embodiments, are not precisely known. In an embodiment, the parameters are specified with an initial value and expected range. After training on the simulation, the machine-learning control system attempts to perform the task in the real world. In an embodiment, the results of the attempt are compared to the expected results of the simulation, and the parameters that govern the simulation are adjusted so that the simulated result matches the real-world attempt. In an embodiment, the machine-learning control system is retrained on the updated simulation. In an embodiment, as additional real-world attempts are made, the simulation parameters are refined and the control system is retrained until the simulation is accurate and the control system is able to successfully perform the task in the real world.

Simulation of tasks using neural networks

Apparatuses, systems, and techniques apply to a force-based (e.g., primal) formulation for object simulation. In at least one embodiment, updates to the force-based formulation is determined by solving for constraints that are to be satisfied when simulating rigid bodies (e.g., contact rich scenarios).

Methods of contact for simulation

Candidate grasping models of a deformable object are applied to generate a simulation of a response of the deformable object to the grasping model. From the simulation, grasp performance metrics for stress, deformation controllability, and instability of the response to the grasping model are obtained, and the grasp performance metrics are correlated with robotic grasp features.

Method for assessing the quality of a robotic grasp on 3D deformable objects

A cable driving a large system such as cable driven machines, cable cars or tendons in a human or robot is typically modeled as a large number of small segments that are connected via joints. The two main difficulties with this model are satisfying the inextensibility constraint and handling the typically large mass ratio between the segments and the objects they connect. This disclosure introduces an effective approach to solving these problems. The introduced approach simulates the effect of a cable using a new type of distance constraint called 'cable joint' that changes both its attachment points and its rest length dynamically. The introduced approach models a cable connecting a series of objects, e.g., components of a robot, as a sequence of cable joints, reducing the complexity of the simulation from the order of the number of segments in the cable to the number of connected objects.

Simulating a cable driven system representative of a robot

Embodiments of the present invention provide a position-based dynamics approach for simulating objects using a set of points and constraints, applied as equations that restrict the relative motion of bodies. Forces are applied to the points to move them, and the constraints ensure that the points will not move in a way that is inconsistent with rules of the simulation. The present invention improves upon existing PBD approaches by using regularized constraints that directly correspond to well-defined energy potentials, and which can advantageously be solved independent of time step and iteration count.

Position-based dynamics simulation

This disclosure presents a process to generate one or more video frames through guiding the movements of a target object in an environment controlled by physics-based constraints. The target object is guided by the movements of a reference object from a motion capture (MOCAP) video clip. As disturbances, environmental factors, or other physics-based constraints interfere with the target object mimicking the reference object. A tracking agent, along with a corresponding neural network, can be used to compensate and modify the movements of the target object. Should the target object diverge significantly from the reference object, such as falling down, a recovery agent, along with a corresponding neural network, can be used to move the target object back into an approximate alignment with the reference object before resuming the tracking process.

Imitating motion capture clips using a neural network

A cable driving a large system such as cable driven machines, cable cars or tendons in a human or robot is typically modeled as a large number of small segments that are connected via joints. The two main difficulties with this approach are satisfying the inextensibility constraint and handling the typically large mass ratio between the small segments and the larger objects they connect. This disclosure introduces a more effective approach to solving these problems. The introduced approach simulates the effect of a cable instead of the cable itself using a new type of distance constraint called 'cable joint' that changes both its attachment points and its rest length dynamically. The introduced approach models a cable connecting a series of objects as a sequence of cable joints, reducing the complexity of the simulation from the order of the number of segments in the cable to the number of connected objects.

Simulating a cable driven system by simulating the effect of cable portions on objects of the system

Embodiments of the present invention provide a novel method and discretization for animating water waves. The approaches disclosed combine the flexibility of a numerical approach to wave simulation with the stability and visual detail provided by a spectrum-based approach to provide Eulerian methods for simulating large-scale oceans with highly detailed wave features. A graphics processing unit stores a one-dimensional texture referred to as a wave profile buffer that stores pre-computed results at a number of discrete sample points for performing wave height evaluation. The water surface is rendered according to water height values computed using the wave profile, accounting for advection, spatial diffusion, angular diffusion, boundary reflections, and dissipation.

Systems and methods for computer simulation of detailed waves for large-scale water simulation

Embodiments of the present invention provide a method for simulating deformable solids undergoing large plastic deformation and topological changes using shape matching. Positional information for particles and orientation information from clusters is used to simulate deformable solids represented by particles. Each visual vertex stores references to particles that influence the vertex, and stores the local position of the particles. A two-step method interpolates orientation from clusters to particles, and uses the orientation and position of particles to skin the visual mesh vertices. This results in a fast method that can reproduce rotation and does not require the visual mesh vertex to be located within a convex hull of particles.

Skinning a cluster based simulation with a visual mesh using interpolated orientation and position

A strain based dynamic technique, for rendering special effects, includes simulation as a function of a Green-St. Venant strain tensor constraint. The behavior of a soft body may be controlled independent of a mesh structure by assigning different stiffness values to each constraint of the Green-St. Venant strain tensor.

Strain based dynamics for rendering special effects

A computer implemented method of simulating a stack of objects represented as data within memory of a computer system is disclosed. The method comprises modeling the stack within a computer simulation as a set of associated primitives with associated constraints thereto in the memory, wherein the stack comprises a plurality of layers and wherein each layer comprises at least one primitive. The method further comprises estimating a height for each of the primitives in the stack and determining a respective scaling factor for each of the primitives in parallel, wherein each scaling factor is operable to adjust a mass value of each of the primitives. Also, the method comprises scaling a mass value of each of the primitives in accordance with a respective scaling factor in parallel. Finally, the method comprises solving over a plurality of constraints iteratively using a scaled mass value for each of the primitives.

Method and apparatus for simulating stiff stacks

A method for simulating visual effects is disclosed. The method comprises modeling each visual effect within a simulation as a set of associated particles with associated constraints applicable thereto. It also comprises predicting first velocities and first positions of a plurality of particles being used to simulate a visual effect based on an external force applied to the plurality of particles. Next, it comprises identifying a set of neighboring particles for each of the plurality of particles. The method also comprises solving a plurality of constraints related to the visual effect, wherein each of the plurality of constraints is solved for the plurality of particles in parallel. Lastly, responsive to the solving, the method comprises determining second velocities and second positions for the plurality of particles.

Growing community of inventors

Auckland, New Zealand

Miles Macklin