Don't hesitate to leave issues or discussions to me if there are any corrections or errors.
🔤 The items below are in alphabetical order.
- Boston Dynamics Spot Robot | All of its Engineering SECRETS!
- Development of quadruped walking robots: A review
- Quadruped Robot Basics
Platforms
It could include abroad keywords related to quadrupedal walking robots, e.g. control methods or reinforcement learning
2024
- Accessorizing Quadrupedal Robots with Wearable Electronics
- Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion
- DTC: Deep Tracking Control
- Learning Quadrupedal High-Speed Running on Uneven Terrain
- Legged Robot State Estimation With Invariant Extended Kalman Filter Using Neural Measurement Network
- OptiState: State Estimation of Legged Robots using Gated Networks with Transformer-based Vision and Kalman Filtering
- Pedipulate: Enabling Manipulation Skills using a Quadruped Robot's Leg
- ProNav: Proprioceptive Traversability Estimation for Legged Robot Navigation in Outdoor Environments
- Reduced Model Predictive Control Toward Highly Dynamic Quadruped Locomotion
2023
![](./assets/2023.png)
- Adaptive Locomotion Learning for Quadruped Robots by Combining DRL with a Cosine Oscillator Based Rhythm Controller
- Adaptive walking control for quadruped robot by using oscillation patterns
- AMP in the wild: Learning robust, agile, natural legged locomotion skills
- ARMP: Autoregressive Motion Planning for Quadruped Locomotion and Navigation in Complex Indoor Environments
- ArtPlanner: Robust Legged Robot Navigation in the Field
- ASC: Adaptive Skill Coordination for Robotic Mobile Manipulation
- Autonomous Stair Ascending and Descending by Quadruped Wheelchairs
- Barkour: Benchmarking Animal-level Agility with Quadruped Robots
- Barry: A High-Payload and Agile Quadruped Robot
- Combining model-predictive control and predictive reinforcement learning for stable quadrupedal robot locomotion
- Curiosity-Driven Learning of Joint Locomotion and Manipulation Tasks
- DeepTransition: Viability Leads to the Emergence of Gait Transitions in Learning Anticipatory Quadrupedal Locomotion Skills
- DOC: Differentiable Optimal Control for Retargeting Motions onto Legged Robots
- Dojo: A Differentiable Physics Engine for Robotics
- DreamWaQ: Learning Robust Quadrupedal Locomotion With Implicit Terrain Imagination via Deep Reinforcement Learning
- DribbleBot: Dynamic Legged Manipulation in the Wild
- Drilling Task with a Quadruped Robot for Silage Face Measurements
- DTC: Deep Tracking Control - A Unifying Approach to Model-Based Planning and Reinforcement-Learning for Versatile and Robust Locomotion
- Event Camera-based Visual Odometry for Dynamic Motion Tracking of a Legged Robot Using Adaptive Time Surface
- Event-based Agile Object Catching with a Quadrupedal Robot
- Extreme Parkour with Legged Robots
- Fast Traversability Estimation for Wild Visual Navigation
- From Data-Fitting to Discovery: Interpreting the Neural Dynamics of Motor Control through Reinforcement Learning
- Geometric Mechanics of Contact-Switching Systems
- Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion
- Guardians as You Fall: Active Mode Transition for Safe Falling
- Hierarchical Experience-informed Navigation for Multi-modal Quadrupedal Rebar Grid Traversal
- Identifying important sensory feedback for learning locomotion skills
- Intelligent Control of Multilegged Robot Smooth Motion: A Review
- iPlanner: Imperative Path Planning
- Language to Rewards for Robotic Skill Synthesis
- Layered Control for Cooperative Locomotion of Two Quadrupedal Robots: Centralized and Distributed Approaches
- Learning a Single Policy for Diverse Behaviors on a Quadrupedal Robot using Scalable Motion Imitation
- Learning and Adapting Agile Locomotion Skills by Transferring Experience
- Learning Arm-Assisted Fall Damage Reduction and Recovery for Legged Mobile Manipulators
- Learning Complex Motor Skills for Legged Robot Fall Recovery
- Learning Impulse-Reduced Gait for Quadruped Robot using CMA-ES
- Learning Low-Frequency Motion Control for Robust and Dynamic Robot Locomotion
- Learning quadrupedal locomotion on deformable terrain
- Learning to Exploit Elastic Actuators for Quadruped Locomotion
- Learning to Walk by Steering: Perceptive Quadrupedal Locomotion in Dynamic Environments
- Legs as Manipulator: Pushing Quadrupedal Agility Beyond Locomotion
- Lifelike Agility and Play on Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models
- LSC: Language-guided Skill Coordination
- LSTP: Long Short-Term Motion Planning for Legged and Legged-Wheeled Systems
- Mastering Diverse Domains through World Models
- Max: A Wheeled-Legged Quadruped Robot for Multimodal Agile Locomotion
- Multi-Contact Whole Body Force Control for Position-Controlled Robots
- Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotion
- OPT-Mimic: Imitation of Optimized Trajectories for Dynamic Quadruped Behaviors
- ORBIT: A Unified Simulation Framework for Interactive Robot Learning Environments
- Orthrus: A Dual-arm Quadrupedal Robot for Mobile Manipulation and Entertainment Applications
- PyPose: A Library for Robot Learning with Physics-based Optimization
- Real-Time Collision-Free Motion Planning and Control for Mobile Manipulation with Quadrupeds
- Reinforcement Learning for Legged Robots: Motion Imitation from Model-Based Optimal Control
- Reinforcement Learning from Multiple Sensors via Joint Representations
- Resilient Legged Local Navigation: Learning to Traverse with Compromised Perception End-to-End
- Responsive CPG-Based Locomotion Control for Quadruped Robots
- RL + Model-based Control: Using On-demand Optimal Control to Learn Versatile Legged Locomotion
- RoboHive: A Unified Framework for Robot Learning
- Robot Parkour Learning
- Robust Quadrupedal Locomotion via Risk-Averse Policy Learning
- Robust Recovery Motion Control for Quadrupedal Robots via Learned Terrain Imagination
- Roll-Drop: accounting for observation noise with a single parameter
- SafeSteps: Learning Safer Footstep Planning Policies for Legged Robots via Model-Based Priors
- SayTap: Language to Quadrupedal Locomotion
- Scientific Exploration of Challenging Planetary Analog Environments with a Team of Legged Robots
- Skill Graph for Real-world Quadrupedal Robot Reinforcement Learning
- SLoMo: A General System for Legged Robot Motion Imitation From Casual Videos
- Solving Challenging Control Problems via Learning-based Motion Planning and Imitation
- Taking the First Step Toward Autonomous Quadruped Robots: The Quadruped Robot Challenge at ICRA 2023 in London [Competitions]
- Towards Legged Locomotion on Steep Planetary Terrain
- Tuning Legged Locomotion Controllers via Safe Bayesian Optimization
- Versatile Multi-Contact Planning and Control for Legged Loco-Manipulation
2022
![](./assets/2022.png)
- A Collision-Free MPC for Whole-Body Dynamic Locomotion and Manipulation
- A Linearization of Centroidal Dynamics for the Model-Predictive Control of Quadruped Robots
- A Reconfigurable Leg for Walking Robots
- A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning
- A Whole-Body Controller Based on a Simplified Template for Rendering Impedances in Quadruped Manipulators
- A1 SLAM: Quadruped SLAM using the A1's Onboard Sensors
- Accelerated Policy Learning with Parallel Differentiable Simulation
- Accessibility-Based Clustering for Efficient Learning of Locomotion Skills
- Advanced Skills by Learning Locomotion and Local Navigation End-to-End
- Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learning
- Agile and versatile climbing on ferromagnetic surfaces with a quadrupedal robot
- Animal Motions on Legged Robots Using Nonlinear Model Predictive Control
- Bio-Inspired Rhythmic Locomotion for Quadruped Robots
- Central pattern generators evolved for real-time adaptation
- Cerberus: Low-Drift Visual-Inertial-Leg Odometry For Agile Locomotion
- Collision-Backpropagation based Obstacle Avoidance Method for a Legged Robot Expressed as a Simplified Dynamics Model
- Combining Learning-Based Locomotion Policy With Model-Based Manipulation for Legged Mobile Manipulators
- Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotion
- Control of Wheeled-Legged Quadrupeds Using Deep Reinforcement Learning
- Coupling Vision and Proprioception for Navigation of Legged Robots
- CPG-RL: Learning Central Pattern Generators for Quadruped Locomotion
- Creating a Dynamic Quadrupedal Robotic Goalkeeper with Reinforcement Learning
- DayDreamer: World Models for Physical Robot Learning
- Deep Hierarchical Planning from Pixels
- Deep reinforcement learning for real-world quadrupedal locomotion: a comprehensive review
- Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion
- DeepPhase: periodic autoencoders for learning motion phase manifolds
- Elevation Mapping for Locomotion and Navigation using GPU
- Factor Graph Fusion of Raw GNSS Sensing with IMU and Lidar for Precise Robot Localization without a Base Station
- GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots
- Hierarchical Adaptive Loco-manipulation Control for Quadruped Robots
- Hierarchical Decentralized Deep Reinforcement Learning Architecture for a Simulated Four-Legged Agent
- Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robot
- High-speed quadrupedal locomotion by imitation-relaxation reinforcement learning
- Human Motion Control of Quadrupedal Robots using Deep Reinforcement Learning
- Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors
- Is Conditional Generative Modeling all you need for Decision-Making?
- Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic Locomotion
- Landing control method of a lightweight four-legged landing and walking robot
- Layered Control for Cooperative Locomotion of Two Quadrupedal Robots: Centralized and Distributed Approaches
- Learning a Unified Policy for Whole-Body Control of Manipulation and Locomotion
- Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations
- Learning and Deploying Robust Locomotion Policies with Minimal Dynamics Randomization
- Learning Footstep Planning for the Quadrupedal Locomotion with Model Predictive Control
- Learning Forward Dynamics Model and Informed Trajectory Sampler for Safe Quadruped Navigation
- Learning Low-Frequency Motion Control for Robust and Dynamic Robot Locomotion
- Learning Modular Robot Visual-motor Locomotion Policies
- Learning plastic matching of robot dynamics in closed-loop central pattern generators
- Learning robust perceptive locomotion for quadrupedal robots in the wild
- Learning Torque Control for Quadrupedal Locomotion
- Learning Visual Locomotion with Cross-Modal Supervision
- Legged Locomotion in Challenging Terrains using Egocentric Vision
- Locomotion Policy Guided Traversability Learning using Volumetric Representations of Complex Environments
- Meta Reinforcement Learning for Optimal Design of Legged Robots
- Model Predictive Control of Quadruped Robot Based on Reinforcement Learning
- Monte Carlo Tree Search Gait Planner for Non-Gaited Legged System Control
- Multi-Modal Legged Locomotion Framework With Automated Residual Reinforcement Learning
- Neural Scene Representation for Locomotion on Structured Terrain
- Next Steps: Learning a Disentangled Gait Representation for Versatile Quadruped Locomotion
- Nonlinear Model Predictive Control for Quadrupedal Locomotion Using Second-Order Sensitivity Analysis
- Online Kinematic Calibration for Legged Robots
- Perceptive Locomotion through Nonlinear Model Predictive Control
- PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations
- PrePARE: Predictive Proprioception for Agile Failure Event Detection in Robotic Exploration of Extreme Terrains
- PSTO: Learning Energy-Efficient Locomotion for Quadruped Robots
- Quadruped Reinforcement Learning without Explicit State Estimation
- Rapid and Reliable Quadruped Motion Planning with Omnidirectional Jumping
- Rapid Locomotion via Reinforcement Learning
- Real-time Digital Double Framework to Predict Collapsible Terrains for Legged Robots
- REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer
- RLOC: Terrain-Aware Legged Locomotion using Reinforcement Learning and Optimal Control
- RoLoMa: Robust Loco-Manipulation for Quadruped Robots with Arms
- Safe Reinforcement Learning for Legged Locomotion
- Sample Efficient Dynamics Learning for Symmetrical Legged Robots:Leveraging Physics Invariance and Geometric Symmetries
- Saving the Limping: Fault-tolerant Quadruped Locomotion via Reinforcement Learning
- State Estimation for Hybrid Locomotion of Driving-Stepping Quadrupeds
- STEP: State Estimator for Legged Robots Using a Preintegrated foot Velocity Factor
- TROT-Q: Traversability and Obstacle Aware Target Tracking System for Quadruped Robots
- Unsupervised Learning of Terrain Representations for Haptic Monte Carlo Localization
- VAE-Loco: Versatile Quadruped Locomotion by Learning a Disentangled Gait Representation
- Versatile Real-Time Motion Synthesis via Kino-Dynamic MPC with Hybrid-Systems DDP
- Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions
- ViNL: Visual Navigation and Locomotion Over Obstacles
- ViTAL: Vision-Based Terrain-Aware Locomotion for Legged Robots
- Walk These Ways: Gait-conditioned Policies Yield Diversified Quadrupedal Agility
- Walking in Narrow Spaces: Safety-critical Locomotion Control for Quadrupedal Robots with Duality-based Optimization
2021
![](./assets/2021.png)
- A Review of Physics Simulators for Robotic Applications
- A Unified MPC Framework for Whole-Body Dynamic Locomotion and Manipulation
- Adaptive CLF-MPC With Application to Quadrupedal Robots
- Adaptive Force-based Control for Legged Robots
- Animal Gaits on Quadrupedal Robots Using Motion Matching and Model-Based Control
- Cat-Like Jumping and Landing of Legged Robots in Low Gravity Using Deep Reinforcement Learning
- Circus ANYmal: A Quadruped Learning Dexterous Manipulation with Its Limbs
- CPG-ACTOR: Reinforcement Learning for Central Pattern Generators
- Development of a Quadruped Robot System With Torque-Controllable Modular Actuator Unit
- Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotion
- Efficient Motion Planning Based on Kinodynamic Model for Quadruped Robots Following Persons in Confined Spaces
- GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model
- Imitation Learning by Reinforcement Learning
- Imitation Learning from MPC for Quadrupedal Multi-Gait Control
- Jumping over obstacles with MIT Cheetah 2
- Learning Agile Locomotion Skills with a Mentor
- Learning Fast Adaptation with Meta Strategy Optimization
- Learning multiple gaits of quadruped robot using hierarchical reinforcement learning
- Learning to Jump from Pixels
- Learning to Navigate Sidewalks in Outdoor Environments
- Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning
- Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers
- Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World
- Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robots
- Obstacle Overcoming Gait Design for Quadruped Robot with Vision and Tactile Sensing Feedback
- Perceptive Autonomous Stair Climbing for Quadrupedal Robots
- Real-time Optimal Navigation Planning Using Learned Motion Costs
- Reinforcement Learning for Collaborative Quadrupedal Manipulation of a Payload over Challenging Terrain
- Reinforcement Learning with Evolutionary Trajectory Generator: A General Approach for Quadrupedal Locomotion
- Representation-Free Model Predictive Control for Dynamic Motions in Quadrupeds
- RMA: Rapid Motor Adaptation for Legged Robots
- Robust High-speed Running for Quadruped Robots via Deep Reinforcement Learning
- Search-based Kinodynamic Motion Planning for Omnidirectional Quadruped Robots
- Simulation-Based Climbing Capability Analysis for Quadrupedal Robots
- Traversing Steep and Granular Martian Analog Slopes With a Dynamic Quadrupedal Robot
- VILENS: Visual, Inertial, Lidar, and Leg Odometry for All-Terrain Legged Robots
- VILENS: Visual, Inertial, Lidar, and Leg Odometryfor All-Terrain Legged Robots
- Vision-based Terrain Perception of Quadruped Robots in Complex Environments
- Visual-Locomotion: Learning to Walk on Complex Terrains with Vision
2020
![](./assets/2020.png)
- An Open Torque-Controlled Modular Robot Architecture for Legged Locomotion Research
- Dream to Control: Learning Behaviors by Latent Imagination
- Dynamic equilibrium of climbing robots based on stability polyhedron for gravito-inertial acceleration
- Dynamics-Aware Unsupervised Discovery of Skills
- Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning
- First Steps: Latent-Space Control with Semantic Constraints for Quadruped Locomotion
- Guided Constrained Policy Optimization for Dynamic Quadrupedal Robot Locomotion
- Learning Agile Robotic Locomotion Skills by Imitating Animals
- Learning quadrupedal locomotion over challenging terrain
- Learning to Walk in the Real World with Minimal Human Effort
- Models, Pixels, and Rewards: Evaluating Design Trade-offs in Visual Model-Based Reinforcement Learning
- Mpc-based controller with terrain insight for dynamic legged locomotion
- Multi-expert learning of adaptive legged locomotion
- One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control
- Path Planning With Local Motion Estimations
- Perceptive Locomotion in Rough Terrain – Online Foothold Optimization
- Plane-based stairway mapping for legged robot locomotion
- Pronto: A Multi-Sensor State Estimator for Legged Robots in Real-World Scenarios
- Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning
- Reinforcement learning for quadrupedal locomotion with design of continual–hierarchical curriculum
- Vision Aided Dynamic Exploration of Unstructured Terrain with a Small-Scale Quadruped Robot
2019
![](./assets/2019.png)
- DeepGait: Planning and Control of Quadrupedal Gaits using Deep Reinforcement Learning
- Design a Fall Recovery Strategy for a Wheel-Legged Quadruped Robot Using Stability Feature Space
- Dynamic Locomotion on Slippery Ground
- Fast and Continuous Foothold Adaptation for Dynamic Locomotion through CNNs
- Feedback MPC for Torque-Controlled Legged Robots
- Hierarchical Reinforcement Learning for Quadruped Locomotion
- Highly Dynamic Quadruped Locomotion via Whole-Body Impulse Control and Model Predictive Control
- Learning agile and dynamic motor skills for legged robots
- Model Predictive Control for Motion Planning of Quadrupedal Locomotion
- Policies Modulating Trajectory Generators
- Robust Legged Robot State Estimation Using Factor Graph Optimization
- SpaceBok: A Dynamic Legged Robot for Space Exploration
- Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction
- Whole-body motion and landing force control for quadrupedal stair climbing
2018
![](./assets/2018.png)
- Contact Model Fusion for Event-Based Locomotion in Unstructured Terrains
- Dynamic locomotion in the MIT Cheetah 3 through convex model-predictive control
- Gait and Trajectory Optimization for Legged Systems Through Phase-Based End-Effector Parameterization
- Learning to Walk via Deep Reinforcement Learning
- MIT Cheetah 3: Design and Control of a Robust, Dynamic Quadruped Robot
- Mode-adaptive neural networks for quadruped motion control
- Per-Contact Iteration Method for Solving Contact Dynamics
- Policy Transfer with Strategy Optimization
- Robust rough-terrain locomotion with a quadrupedal robot
- Robust Rough-Terrain Locomotion with a Quadrupedal Robot
- Scalability Analysis of Legged Robots for Space Exploration
- Sim-to-Real: Learning Agile Locomotion For Quadruped Robots
~ 2017
![](./assets/2017.png)
- ANYmal - a highly mobile and dynamic quadrupedal robot
- Design of HyQ – a hydraulically and electrically actuated quadruped robot
- High-slope terrain locomotion for torque-controlled quadruped robots
- Meta Learning Shared Hierarchies
- Robot-Centric Elevation Mapping with Uncertainty Estimates
- Slip Detection and Recovery for Quadruped Robots
- State Estimation for Legged Robots - Consistent Fusion of Leg Kinematics and IMU
- Survey of Numerical Methods for Trajectory Optimization
- Terrain-adaptive locomotion skills using deep reinforcement learning
- Tumble stability criterion of integrated locomotion and manipulation
- Wholebody trajectory optimization for non-periodic dynamic motions on quadrupedal systems
Channels
- AI Robotics Seminar - University of Toronto
- ANYbotics
- Biomimetics MIT
- Boston Dynamics
- CMU Robotic Exploration Lab
- cmurobotics
- Conference on Robot Learning
- DeepMind
- DeepRobotics
- Dynamic Robotics Laboratory - Oregon State University
- Erwin Coumans
- ETH Zürich
- Figure AI
- Ghost Robotics
- Hybrid Robotics
- IHMC Robotics
- KAIST Urban Robotics Lab
- magnecko
- MIT Robotics
- MPCRL 2021 - Recent advances in MPC and RL for legged robots
- Northwestern Robotics
- Oxford Dynamic Robot Systems Group
- PRO ROBOTS
- RaiLab Kaist
- RcLab
- Reinforcement Learning Zurich
- RISE LAB - SKKU
- Robomechanics Lab
- robot mania
- Robotics Innovatory
- Robotics Today
- Stoch Lab IISc
- The Robot Brains Podcast
- umrobotics
- Unitree Robotics
Homepages
- Biomimetic Robotics Lab - MIT
- Computational Robotics Lab - ETH
- Dynamic and Autonomous Robotic Systems (DARoS) Laboratory - University of Massachusetts Amherst
- Dynamic Legged Systems Lab - Istituto Italiano di Tecnologia
- Dynamic Robot Systems Group - University of Oxford
- Hybrid Robotics Lab - UC Berkely
- RAI Lab - KAIST
- RcLab - Kookmin University
- Robomechanics Lab - Carnegie Mellon University
- Robotic System Lab - ETH Zürich
- Robotics Innovatory - SungKyunKwan University
- Stochastic Robotics Lab (StochLab) - IISc
- The Robotics Lab - IDSIA
More
Extended to Bipedal(Legged) Robots
Research
- FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning
- Hybrid Stepping Motion Generation for Wheeled-Bipedal Robots Without Roll Joints on Legs
- Learning hybrid locomotion skills—Learn to exploit residual actions and modulate model-based gait control
- Learning Vision-Based Bipedal Locomotion for Challenging Terrain
- Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Models
- Real-World Humanoid Locomotion with Reinforcement Learning
Github Repositories
Labs & Companies