DART: Dynamic Animation and Robotics Toolkit

Lee, Jeongseok; Grey, Michael X.; Ha, Sehoon; Kunz, Tobias; Jain, Sumit; Ye, Yuting; Srinivasa, Siddhartha S.; Stilman, Mike; Liu, C. Karen

doi:10.21105/joss.00500

Cited by 226 publications

(149 citation statements)

References 5 publications

Supporting

Mentioning

141

Contrasting

Unclassified

Order By: Relevance

“…We use DART [10] as the simulator which provides realistic physics simulation. We use blender to randomly generate objects' meshes, which can be imported to DART.…”

Section: B Data Preparationmentioning

confidence: 99%

Push-Net: Deep Planar Pushing for Objects with Unknown Physical Properties

Li¹,

Lee²,

Hsu³

2018

Robotics: Science and Systems XIV

View full text Add to dashboard Cite

Fig. 1: Push-Net enables both a Fetch arm and a Kinova MICO arm to robustly and efficiently push novel objects of unknown physical properties for re-positioning and re-orientation on a 2D plane.Abstract-This paper introduces Push-Net, a deep recurrent neural network model, which enables a robot to push objects of unknown physical properties for re-positioning and re-orientation, using only visual camera images as input. The unknown physical properties is a major challenge for pushing. Push-Net overcomes the challenge by tracking a history of push interactions with an LSTM module and training an auxiliary objective function that estimates an object's center of mass. We trained Push-Net entirely in simulation and tested it extensively on many different objects in both simulation and on two real robots, a Fetch arm and a Kinova MICO arm. Experiments suggest that Push-Net is robust and efficient. It achieved over 97% success rate in simulation on average and succeeded in all real robot experiments with a small number of pushes.

show abstract

“…We use DART [10] as the simulator which provides realistic physics simulation. We use blender to randomly generate objects' meshes, which can be imported to DART.…”

Section: B Data Preparationmentioning

confidence: 99%

Push-Net: Deep Planar Pushing for Objects with Unknown Physical Properties

Li¹,

Lee²,

Hsu³

2018

Robotics: Science and Systems XIV

View full text Add to dashboard Cite

show abstract

“…To create the ice environment, we set the friction coefficient of the ground to 0.02 [Mil08]. We used the Dart [LGH*18] open source engine for the simulation. Simulation time rate is 1.2 kHz.…”

Section: Experiments and Resultsmentioning

confidence: 99%

Figure Skating Simulation from Video

Park

Lee

2019

Computer Graphics Forum

View full text Add to dashboard Cite

Figure skating is one of the most popular ice sports at the Winter Olympic Games. The skaters perform several skating skills to express the beauty of the art on ice. Skating involves moving on ice while wearing skate shoes with thin blades; thus, it requires much practice to skate without losing balance. Moreover, figure skating presents dynamic moves, such as jumping, artistically. Therefore, demonstrating figure skating skills is even more difficult to achieve than basic skating, and professional skaters often fall during Winter Olympic performances. We propose a system to demonstrate figure skating motions with a physically simulated human‐like character. We simulate skating motions with non‐holonomic constraints, which make the skate blade glide on the ice surface. It is difficult to obtain reference motions from figure skaters because figure skating motions are very fast and dynamic. Instead of using motion capture data, we use key poses extracted from videos on YouTube and complete reference motions using trajectory optimization. We demonstrate figure skating skills, such as crossover, three‐turn, and even jump. Finally, we use deep reinforcement learning to generate a robust controller for figure skating skills.

show abstract

“…We simulated the physical interactions between the human and robot with the Dynamic Animation and Robotics Toolkit (DART) [32] at 400Hz. We included an additional data driven joint limiting constraint demonstrated by [33] for the shoulders and elbows of the human to more accurately model the range of motion for these joints.…”

Section: Methodsmentioning

confidence: 99%

Learning to Collaborate From Simulation for Robot-Assisted Dressing

Clegg

Erickson

Grady

et al. 2020

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

We investigated the application of haptic aware feedback control and deep reinforcement learning to robot assisted dressing in simulation. We did so by modeling both human and robot control policies as separate neural networks and training them both via TRPO. We show that co-optimization, training separate human and robot control policies simultaneously, can be a valid approach to finding successful strategies for human/robot cooperation on assisted dressing tasks. Typical tasks are putting on one or both sleeves of a hospital gown or pulling on a T-shirt. We also present a method for modeling human dressing behavior under variations in capability including: unilateral muscle weakness, Dyskinesia, and limited range of motion. Using this method and behavior model, we demonstrate discovery of successful strategies for a robot to assist humans with a variety of capability limitations.*

show abstract

DART: Dynamic Animation and Robotics Toolkit

Cited by 226 publications

References 5 publications

Push-Net: Deep Planar Pushing for Objects with Unknown Physical Properties

Push-Net: Deep Planar Pushing for Objects with Unknown Physical Properties

Figure Skating Simulation from Video

Learning to Collaborate From Simulation for Robot-Assisted Dressing

Contact Info

Product

Resources

About