DeepLoco

By Xue Bin Peng, Glen Berseth, KangKang Yin, Michiel van de Panne. 2017

444 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering, Reinforcement Learning, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

In Reinforcement Learning

In Robotics & Control

Citations in the corpus

Emergence of Locomotion Behaviours in Rich Environments (2017, background): “Impressive results were recently achieved with learned locomotion controllers for a 3D humanoid body [29], but these rely on a domain-speciﬁc structure and human motion capture data to bootstrap the movement skills for navigating ﬂat terrains.”
Offline Reinforcement Learning as One Big Sequence Modeling Problem (2021, methodology): “, 2011); and other areas such as hierarchical RL (Peng et al., 2017; Co-Reyes et al., 2018; Jiang et al., 2019).”
Sim-to-Real: Learning Agile Locomotion For Quadruped Robots (2018, background): “[35] learned a two-level hierarchical controller to direct a 3D biped to walk in a simulated environment.”
Sim-to-Real Transfer of Robotic Control with Dynamics Randomization (2017, background): “The framework has enabled simulated agents to develop highly dynamic motor skills [4], [5], [6], [7].”
Dynamics-Aware Unsupervised Discovery of Skills (2019, neutral): “However, in contrast to end-to-end HRL approaches [30, 54], we can leverage a stable, two-phase learning setup.”
Sim-to-Real Reinforcement Learning for Deformable Object Manipulation (2018, methodology): “has not yet been extensively applied to cloth manipulation, even though it has found applications in many other robotic domains, including rigid object manipulation [21, 22], UAV control [23] or bipedal robot control [24].”
Robust Imitation of Diverse Behaviors (2017, background): “Yet, as pointed out in a recent hierarchical control paper [23], the design of such controllers often requires signiﬁcant human insight.”
Learning agile and dynamic motor skills for legged robots (2019, background): “[22, 24, 25].”
Language as an Abstraction for Hierarchical Deep Reinforcement Learning (2019, background): “Hard-coded abstractions often lack modeling flexibility and are task-specific [63, 33, 26, 47], while learned abstractions often find degenerate solutions without careful tuning [5, 24].”
Deep Local Trajectory Replanning and Control for Robot Navigation (2019, background): “Building on a long tradition in robotics [43, 44, 45, 46, 11],”
Robot Parkour Learning (2023, background): “[29, 61, 31], elevation maps [28, 109, 110, 111, 112], lidar scans [113], RGB images [32], event cameras [68] or learned neural spaces [30, 33], but none have demonstrated effective high-speed agile locomotion.”
Legged Locomotion in Challenging Terrains using Egocentric Vision (2022, methodology): “Recent methods skip 248 foothold planning and directly train a deep RL policy that takes the elevation map as input and outputs 249 either low-level motor primitives [9, 70] or raw joint angles [14, 71, 72, 73].”
Ego-Pose Estimation and Forecasting As Real-Time PD Control (2019, methodology): “DeepRL based approaches have utilized reference motions to shape the reward function [37, 39].”
Learning human behaviors from motion capture by adversarial imitation (2017, background): “Exciting recent work has used deep RL for 2D locomotion of creatures [20] and very recently for 3D humanoid [21].”
Neural state machine for character-scene interactions (2019, methodology): “Peng et al. [2018a; 2017; 2018b]. cope with this problem by providing reference motion capture data [Peng et al. 2018a, 2017] or video data [Peng et al. 2018b].”