Crossing the reality gap: A survey on sim-to-real transferability of robot controllers in reinforcement learning

E Salvato, G Fenu, E Medvet, FA Pellegrino - IEEE Access, 2021 - ieeexplore.ieee.org
The growing demand for robots able to act autonomously in complex scenarios has widely
accelerated the introduction of Reinforcement Learning (RL) in robots control applications …

Robot learning from randomized simulations: A review

F Muratore, F Ramos, G Turk, W Yu… - Frontiers in Robotics …, 2022 - frontiersin.org
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 …

Epopt: Learning robust neural network policies using model ensembles

A Rajeswaran, S Ghotra, B Ravindran… - arXiv preprint arXiv …, 2016 - arxiv.org
Sample complexity and safety are major challenges when learning policies with
reinforcement learning for real-world tasks, especially when the policies are represented …

Sfv: Reinforcement learning of physical skills from videos

XB Peng, A Kanazawa, J Malik, P Abbeel… - ACM Transactions On …, 2018 - dl.acm.org
Data-driven character animation based on motion capture can produce highly naturalistic
behaviors and, when combined with physics simulation, can provide for natural procedural …

Mujoco: A physics engine for model-based control

E Todorov, T Erez, Y Tassa - 2012 IEEE/RSJ international …, 2012 - ieeexplore.ieee.org
We describe a new physics engine tailored to model-based control. Multi-joint dynamics are
represented in generalized coordinates and computed via recursive algorithms. Contact …

Deep reinforcement learning for modeling human locomotion control in neuromechanical simulation

S Song, Ł Kidziński, XB Peng, C Ong, J Hicks… - … of neuroengineering and …, 2021 - Springer
Modeling human motor control and predicting how humans will move in novel environments
is a grand scientific challenge. Researchers in the fields of biomechanics and motor control …

Learning predict-and-simulate policies from unorganized human motion data

S Park, H Ryu, S Lee, S Lee, J Lee - ACM Transactions on Graphics …, 2019 - dl.acm.org
The goal of this research is to create physically simulated biped characters equipped with a
rich repertoire of motor skills. The user can control the characters interactively by modulating …

Learning basketball dribbling skills using trajectory optimization and deep reinforcement learning

L Liu, J Hodgins - ACM Transactions on Graphics (TOG), 2018 - dl.acm.org
Basketball is one of the world's most popular sports because of the agility and speed
demonstrated by the players. This agility and speed makes designing controllers to realize …

Flexible muscle-based locomotion for bipedal creatures

T Geijtenbeek, M Van De Panne… - ACM Transactions on …, 2013 - dl.acm.org
We present a muscle-based control method for simulated bipeds in which both the muscle
routing and control parameters are optimized. This yields a generic locomotion control …

Optimizing locomotion controllers using biologically-based actuators and objectives

JM Wang, SR Hamner, SL Delp, V Koltun - ACM Transactions on …, 2012 - dl.acm.org
We present a technique for automatically synthesizing walking and running controllers for
physically-simulated 3D humanoid characters. The sagittal hip, knee, and ankle degrees-of …