A survey of optimization-based task and motion planning: From classical to learning approaches

Z Zhao, S Cheng, Y Ding, Z Zhou… - IEEE/ASME …, 2024 - ieeexplore.ieee.org
Task and motion planning (TAMP) integrates high-level task planning and low-level motion
planning to equip robots with the autonomy to effectively reason over long-horizon, dynamic …

Optimization-based control for dynamic legged robots

PM Wensing, M Posa, Y Hu, A Escande… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
In a world designed for legs, quadrupeds, bipeds, and humanoids have the opportunity to
impact emerging robotics applications from logistics, to agriculture, to home assistance. The …

Robust multi-agent reinforcement learning via adversarial regularization: Theoretical foundation and stable algorithms

A Bukharin, Y Li, Y Yu, Q Zhang… - Advances in …, 2024 - proceedings.neurips.cc
Abstract Multi-Agent Reinforcement Learning (MARL) has shown promising results across
several domains. Despite this promise, MARL policies often lack robustness and are …

Benefits of overparameterized convolutional residual networks: Function approximation under smoothness constraint

H Liu, M Chen, S Er, W Liao… - … on Machine Learning, 2022 - proceedings.mlr.press
Overparameterized neural networks enjoy great representation power on complex data, and
more importantly yield sufficiently smooth output, which is crucial to their generalization and …

Learning generalizable vision-tactile robotic grasping strategy for deformable objects via transformer

Y Han, K Yu, R Batra, N Boyd, C Mehta… - IEEE/ASME …, 2024 - ieeexplore.ieee.org
Reliable robotic grasping, especially with deformable objects such as fruits, remains a
challenging task due to underactuated contact interactions with a gripper, unknown object …

Real-time deformable-contact-aware model predictive control for force-modulated manipulation

L Wijayarathne, Z Zhou, Y Zhao… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
The force modulation of robotic manipulators has been extensively studied for several
decades. However, it is not yet commonly used in safety-critical applications due to a lack of …

Initial value problem enhanced sampling for closed-loop optimal control design with deep neural networks

X Zhang, J Long, W Hu, J Han - arXiv preprint arXiv:2209.04078, 2022 - arxiv.org
Closed-loop optimal control design for high-dimensional nonlinear systems has been a long-
standing challenge. Traditional methods, such as solving the associated Hamilton-Jacobi …

Trade-Off Between Robustness and Rewards Adversarial Training for Deep Reinforcement Learning Under Large Perturbations

J Huang, HJ Choi, N Figueroa - IEEE Robotics and Automation …, 2023 - ieeexplore.ieee.org
Deep Reinforcement Learning (DRL) has become a popular approach for training robots
due to its generalization promise, complex task capacity and minimal human intervention …

Distributional Cloning for Stabilized Imitation Learning via ADMM

X Zhang, Y Li, Z Zhang, CG Brinton… - … Conference on Data …, 2023 - ieeexplore.ieee.org
The two leading solution paradigms for imitation learning (IL), BC and GAIL, each suffers
from notable drawbacks. BC, a supervised learning approach to mimic expert actions, is …

LipsNet: a smooth and robust neural network with adaptive Lipschitz constant for high accuracy optimal control

X Song, J Duan, W Wang, SE Li… - International …, 2023 - proceedings.mlr.press
Deep reinforcement learning (RL) is a powerful approach for solving optimal control
problems. However, RL-trained policies often suffer from the action fluctuation problem …