Data to 14 Oct 2026

DeepGait: Planning and Control of Quadrupedal Gaits using Deep Reinforcement Learning

arXiv 1909.08399 ↗First posted 18 Sep 2019cs.RO cs.LGcited by 50

Not on the map. Why?

Abstract (arXiv)

This paper addresses the problem of legged locomotion in non-flat terrain. As legged robots such as quadrupeds are to be deployed in terrains with geometries which are difficult to model and predict, the need arises to equip them with the capability to generalize well to unforeseen situations. In this work, we propose a novel technique for training neural-network policies for terrain-aware locomotion, which combines state-of-the-art methods for model-based motion planning and reinforcement learning. Our approach is centered on formulating Markov decision processes using the evaluation of dynamic feasibility criteria in place of physical simulation. We thus employ policy-gradient methods to independently train policies which respectively plan and execute foothold and base motions in 3D environments using both proprioceptive and exteroceptive measurements. We apply our method within a challenging suite of simulated terrain scenarios which contain features such as narrow bridges, gaps and stepping-stones, and train policies which succeed in locomoting effectively in all cases.

Key facts. Cited by 50 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 10; 2023: 4; 2024: 10; 2025: 12; 2026: 6.

50 papers.

Sort:

By area:

2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 512
2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 179
2023Extreme Parkour with Legged Robotscited by 164
2022Legged Locomotion in Challenging Terrains using Egocentric Visioncited by 151
2023Robot Parkour Learningcited by 149
2023DTC: Deep Tracking Controlcited by 56
2022Advanced Skills by Learning Locomotion and Local Navigation End-to-Endcited by 52
2024Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robotscited by 48
2021Learning to Jump from Pixelscited by 45
2021GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Modelcited by 25
2022Learning Visual Locomotion with Cross-Modal Supervisioncited by 25
2022ViNL: Visual Navigation and Locomotion Over Obstaclescited by 23

38 more

2021Escaping from Zero Gradient: Revisiting Action-Constrained Reinforcement Learning via Frank-Wolfe Policy Optimizationcited by 18
2024FlowPG: Action-constrained Policy Gradient with Normalizing Flowscited by 16
2022Visual CPG-RL: Learning Central Pattern Generators for Visually-Guided Quadruped Locomotioncited by 14
2024SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experiencecited by 14
2025BEDI: A Comprehensive Benchmark for Evaluating Embodied Agents on UAVscited by 10
2022Learning to Brachiate via Simplified Model Imitationcited by 9
2022Learning to Walk by Steering: Perceptive Quadrupedal Locomotion in Dynamic Environmentscited by 8
2024Text2Robot: Evolutionary Robot Design from Text Descriptionscited by 8
2024RoboMorph: Evolving Robot Morphology using Large Language Modelscited by 8
2021Learning Perceptual Locomotion on Uneven Terrains using Sparse Visual Observationscited by 5
2025Optimizing Bipedal Locomotion for The 100m Dash With Comparison to Human Runningcited by 5
2021Learning Coordinated Terrain-Adaptive Locomotion by Imitating a Centroidal Dynamics Plannercited by 4
2024FootstepNet: an Efficient Actor-Critic Method for Fast On-line Bipedal Footstep Planning and Forecastingcited by 4
2025Reinforcement Learning for Active Mattercited by 4
2022Generating a Terrain-Robustness Benchmark for Legged Locomotion: A Prototype via Terrain Authoring and Active Learningcited by 3
2025MaskPlanner: Learning-Based Object-Centric Motion Generation from 3D Point Cloudscited by 3
2021Quadruped Locomotion on Non-Rigid Terrain using Reinforcement Learningcited by 2
2022A Transferable Legged Mobile Manipulation Framework Based on Disturbance Predictive Controlcited by 2
2022A Learning System for Motion Planning of Free-Float Dual-Arm Space Manipulator towards Non-Cooperative Objectcited by 2
2025Robust Reward Alignment via Hypothesis Space Batch Cuttingcited by 2
2025Action-Constrained Imitation Learningcited by 2
2026Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specificationscited by 2
2021PM-FSM: Policies Modulating Finite State Machine for Robust Quadrupedal Locomotioncited by 1
2025SATA: Safe and Adaptive Torque-Based Locomotion Policies Inspired by Animal Learningcited by 1
2025Hierarchical Reinforcement Learning and Value Optimization for Challenging Quadruped Locomotioncited by 1
2025Remote Sensing Image Intelligent Interpretation with the Language-Centered Perspective: Principles, Methods and Challengescited by 1
2026GPO: Growing Policy Optimization for Legged Robot Locomotion and Whole-Body Controlcited by 1
2026ContractionPPO: Certified Reinforcement Learning via Differentiable Contraction Layerscited by 1
2026Mind Your Steps: A General Learning Framework for Accurate Humanoid Foothold Trackingcited by 1
2023Adaptive Tracking of a Single-Rigid-Body Character in Various Environmentscited by 0
2024RoboArm-NMP: a Learning Environment for Neural Motion Planningcited by 0
2024Learning Generic and Dynamic Locomotion of Humanoids Across Discrete Terrainscited by 0
2024Optimal Gait Control for a Tendon-driven Soft Quadruped Robot by Model-based Reinforcement Learningcited by 0
2025Self driving algorithm for an active four wheel drive racecarcited by 0
2025Stabilizing Humanoid Robot Trajectory Generation via Physics-Informed Learning and Control-Informed Steeringcited by 0
2025ATRos: Learning Energy-Efficient Agile Locomotion for Wheeled-legged Robotscited by 0
2026Learning Quadrupedal Locomotion for a Heavy Hydraulic Robot Using an Actuator Modelcited by 0
2026Benefits of Low-Cost Bio-Inspiration in the Age of Overparametrizationcited by 0