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 …
Variational inference mpc using normalizing flows and out-of-distribution projection
T Power, D Berenson - arXiv preprint arXiv:2205.04667, 2022 - arxiv.org
We propose a Model Predictive Control (MPC) method for collision-free navigation that uses
amortized variational inference to approximate the distribution of optimal control sequences …
amortized variational inference to approximate the distribution of optimal control sequences …
Learning a Generalizable Trajectory Sampling Distribution for Model Predictive Control
T Power, D Berenson - IEEE Transactions on Robotics, 2024 - ieeexplore.ieee.org
We propose a sample-based model predictive control (MPC) method for collision-free
navigation that uses a normalizing flow as a sampling distribution, conditioned on the start …
navigation that uses a normalizing flow as a sampling distribution, conditioned on the start …
An expeditious and expressive vehicle dynamics model for applications in controls and reinforcement learning
We present a Vehicle Model (VM) that has 17 degrees of freedom and includes nonlinear
tire and powertrain subsystems. Implemented as a relatively small piece of C++ code, the …
tire and powertrain subsystems. Implemented as a relatively small piece of C++ code, the …
Constrained stein variational trajectory optimization
T Power, D Berenson - arXiv preprint arXiv:2308.12110, 2023 - arxiv.org
We present Constrained Stein Variational Trajectory Optimization (CSVTO), an algorithm for
performing trajectory optimization with constraints on a set of trajectories in parallel. We …
performing trajectory optimization with constraints on a set of trajectories in parallel. We …
Path signatures for diversity in probabilistic trajectory optimisation
Motion planning can be cast as a trajectory optimisation problem where a cost is minimised
as a function of the trajectory being generated. In complex environments with several …
as a function of the trajectory being generated. In complex environments with several …
Reactive collision-free motion generation in joint space via dynamical systems and sampling-based MPC
Dynamical system (DS) based motion planning offers collision-free motion, with closed-loop
reactivity thanks to their analytical expression. It ensures that obstacles are not penetrated …
reactivity thanks to their analytical expression. It ensures that obstacles are not penetrated …
Robust control under uncertainty via bounded rationality and differential privacy
V Pacelli, A Majumdar - 2022 International Conference on …, 2022 - ieeexplore.ieee.org
The rapid development of affordable and compact high-fidelity sensors (eg, cameras and
LIDAR) allows robots to construct detailed estimates of their states and environments …
LIDAR) allows robots to construct detailed estimates of their states and environments …
Improving trajectory tracking accuracy for faster and safer autonomous navigation of ground vehicles in off-road settings
Autonomous navigation in off-road settings is complicated by environment-induced
disturbances due to natural phenomena, such as friction and slip. This introduces deviations …
disturbances due to natural phenomena, such as friction and slip. This introduces deviations …
Entropy regularized motion planning via stein variational inference
Many Imitation and Reinforcement Learning approaches rely on the availability of expert-
generated demonstrations for learning policies or value functions from data. Obtaining a …
generated demonstrations for learning policies or value functions from data. Obtaining a …