Robot learning from randomized simulations: A review
The rise of deep learning has caused a paradigm shift in robotics research, favoring
methods that require large amounts of data. Unfortunately, it is prohibitively expensive to …
methods that require large amounts of data. Unfortunately, it is prohibitively expensive to …
Inertial parameter identification in robotics: A survey
This work aims at reviewing, analyzing and comparing a range of state-of-the-art
approaches to inertial parameter identification in the context of robotics. We introduce …
approaches to inertial parameter identification in the context of robotics. We introduce …
Se (3)-diffusionfields: Learning smooth cost functions for joint grasp and motion optimization through diffusion
Multi-objective optimization problems are ubiquitous in robotics, eg, the optimization of a
robot manipulation task requires a joint consideration of grasp pose configurations …
robot manipulation task requires a joint consideration of grasp pose configurations …
NeuralSim: Augmenting differentiable simulators with neural networks
Differentiable simulators provide an avenue for closing the sim-to-real gap by enabling the
use of efficient, gradient-based optimization algorithms to find the simulation parameters that …
use of efficient, gradient-based optimization algorithms to find the simulation parameters that …
Storm: An integrated framework for fast joint-space model-predictive control for reactive manipulation
M Bhardwaj, B Sundaralingam… - … on Robot Learning, 2022 - proceedings.mlr.press
Sampling-based model-predictive control (MPC) is a promising tool for feedback control of
robots with complex, non-smooth dynamics, and cost functions. However, the …
robots with complex, non-smooth dynamics, and cost functions. However, the …
Neural grasp distance fields for robot manipulation
We formulate grasp learning as a neural field and present Neural Grasp Distance Fields
(NGDF). Here, the input is a 6D pose of a robot end effector and output is a distance to a …
(NGDF). Here, the input is a 6D pose of a robot end effector and output is a distance to a …
Synthesizing diverse and physically stable grasps with arbitrary hand structures using differentiable force closure estimator
Existing grasp synthesis methods are either analytical or data-driven. The former one is
oftentimes limited to specific application scope. The latter one depends heavily on …
oftentimes limited to specific application scope. The latter one depends heavily on …
Combining physics and deep learning to learn continuous-time dynamics models
Deep learning has been widely used within learning algorithms for robotics. One
disadvantage of deep networks is that these networks are black-box representations …
disadvantage of deep networks is that these networks are black-box representations …
Neural posterior domain randomization
F Muratore, T Gruner, F Wiese… - … on Robot Learning, 2022 - proceedings.mlr.press
Combining domain randomization and reinforcement learning is a widely used approach to
obtain control policies that can bridge the gap between simulation and reality. However …
obtain control policies that can bridge the gap between simulation and reality. However …
Differentiable physics models for real-world offline model-based reinforcement learning
A limitation of model-based reinforcement learning (MBRL) is the exploitation of errors in the
learned models. Blackbox models can fit complex dynamics with high fidelity, but their …
learned models. Blackbox models can fit complex dynamics with high fidelity, but their …