DART: Dynamic Animation and Robotics Toolkit

By Jeongseok Lee, Michael X. Grey, Sehoon Ha, Tobias Kunz, Sumit Jain, Yuting Ye, Siddhartha S. Srinivasa, Mike Stilman, C. Karen Liu. 2018

306 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

In Robotics & Control

Citations in the corpus

Habitat 2.0: Training Home Assistants to Rearrange their Habitat (2021, background): “PyBullet [38], MuJoCo [29], DART [39], ODE [40], PhysX/FleX [41, 42], and Chrono [43] are primarily physics engines with some level of rendering, while Magnum [44], ORRB [45], and PyRender [46] are primarily renderers.”
From Importance Sampling to Doubly Robust Policy Gradient (2019, positive): “Environments and Approximate Models We use the CartPole Environment in OpenAI Gym (Brockman et al., 2016) with DART physics engine (Lee et al., 2018), and set the horizon length to be 1000.”
Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods (2019, methodology): “Although the focus of this paper is the theoretical insights, we illustrate our results with simulation of learning neural network policies to solve the CartPole balancing task in OpenAI Gym [41] powered by DART physics engine [42].”
IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks (2019, unknown): “stration videos and trajectories can be collected and used for imitation learning, similar to Roboturk [35]. 4.4 Physics Simulation Frameworks Mujoco [3], Unity ML-Agents [36], PyBullet [7], and Dart [37] are some popular frameworks for physics simulation for reinforcement learning. We chose to use ”
iGibson, a Simulation Environment for Interactive Tasks in Large Realistic Scenes (2020, background): “motion of bodies when a force is applied, or flow of liquid particles when being poured) [27, 28, 29, 30, 31, 32].”
Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning (2021, methodology): “Popular physics engines like MuJoCo[6], PyBullet[7], DART[8], Drake[9], V-Rep[10] etc. need large CPU clusters to solve challenging RL tasks naturally face these bottlenecks.”
Learning Novel Policies For Tasks (2019, methodology): “For the physics simulation of the Reacher, Hopper and Deceptive Reacher, we use the DART physics engine (Lee et al., 2018).”
End-to-End Differentiable Physics for Learning and Control (2018, methodology): “, 2013], and DART [Lee et al., 2018], have become ubiquitous tools for the creation and development of deep RL agents.”
Predictor-Corrector Policy Optimization (2018, background): “, 2016) with the DART physics engine (Lee et al., 2018)7.”
The Pinocchio C++ library : A fast and flexible implementation of rigid body dynamics algorithms and their analytical derivatives (2019, background): “jl [12], Drake [13], Bullet [14], DART [15], etc.”
Fast Policy Learning through Imitation and Reinforcement (2018, methodology): “We evaluate LOKI on several robotic control tasks from OpenAI Gym (Brockman et al., 2016) with the DART physics engine (Lee et al., 2018) 8 and compare it with several baselines: TRPO (Schulman et al., 2015a), TRPO from expert, DA GGERE D (the ﬁrst-order version of DA GGER (Ross et al., 2011) in…”
How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies? (2019, methodology): “Specifically, we focus on transferring policies for the environments Hopper and Walker from the Dart simulator [26] to the Mujoco simulator [27].”