A review of physics simulators for robotic applications
The use of simulators in robotics research is widespread, underpinning the majority of recent
advances in the field. There are now more options available to researchers than ever before …
advances in the field. There are now more options available to researchers than ever before …
The neuromechanics of animal locomotion: From biology to robotics and back
P Ramdya, AJ Ijspeert - Science Robotics, 2023 - science.org
Robotics and neuroscience are sister disciplines that both aim to understand how agile,
efficient, and robust locomotion can be achieved in autonomous agents. Robotics has …
efficient, and robust locomotion can be achieved in autonomous agents. Robotics has …
Isaac gym: High performance gpu-based physics simulation for robot learning
V Makoviychuk, L Wawrzyniak, Y Guo, M Lu… - arXiv preprint arXiv …, 2021 - arxiv.org
Isaac Gym offers a high performance learning platform to train policies for wide variety of
robotics tasks directly on GPU. Both physics simulation and the neural network policy …
robotics tasks directly on GPU. Both physics simulation and the neural network policy …
Closing the sim-to-real loop: Adapting simulation randomization with real world experience
We consider the problem of transferring policies to the real world by training on a distribution
of simulated scenarios. Rather than manually tuning the randomization of simulations, we …
of simulated scenarios. Rather than manually tuning the randomization of simulations, we …
igibson 1.0: a simulation environment for interactive tasks in large realistic scenes
We present iGibson 1.0, a novel simulation environment to develop robotic solutions for
interactive tasks in large-scale realistic scenes. Our environment contains 15 fully interactive …
interactive tasks in large-scale realistic scenes. Our environment contains 15 fully interactive …
Adversarial motion priors make good substitutes for complex reward functions
Training a high-dimensional simulated agent with an under-specified reward function often
leads the agent to learn physically infeasible strategies that are ineffective when deployed in …
leads the agent to learn physically infeasible strategies that are ineffective when deployed in …
Accelerated policy learning with parallel differentiable simulation
Deep reinforcement learning can generate complex control policies, but requires large
amounts of training data to work effectively. Recent work has attempted to address this issue …
amounts of training data to work effectively. Recent work has attempted to address this issue …
Object rearrangement using learned implicit collision functions
M Danielczuk, A Mousavian… - 2021 IEEE International …, 2021 - ieeexplore.ieee.org
Robotic object rearrangement combines the skills of picking and placing objects. When
object models are unavailable, typical collision-checking models may be unable to predict …
object models are unavailable, typical collision-checking models may be unable to predict …
Dexgraspnet: A large-scale robotic dexterous grasp dataset for general objects based on simulation
Robotic dexterous grasping is the first step to enable human-like dexterous object
manipulation and thus a crucial robotic technology. However, dexterous grasping is much …
manipulation and thus a crucial robotic technology. However, dexterous grasping is much …
A survey of domain-specific architectures for reinforcement learning
M Rothmann, M Porrmann - IEEE Access, 2022 - ieeexplore.ieee.org
Reinforcement learning algorithms have been very successful at solving sequential decision-
making problems in many different problem domains. However, their training is often time …
making problems in many different problem domains. However, their training is often time …