# Agile Maneuvers in Legged Robots: a Predictive Control Approach

arXiv: https://arxiv.org/abs/2203.07554 · HTML: https://mlsanity.com/paper/2203.07554/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 89 references that are in the map.
- First posted on arXiv 14 Mar 2022.

## Builds on (most cited first, 28 of 28)

- [Crocoddyl: An Efficient and Versatile Framework for Multi-Contact Optimal Control](https://mlsanity.com/paper/1909.04947/) (2019)
- [An Open Torque-Controlled Modular Robot Architecture for Legged Locomotion Research](https://mlsanity.com/paper/1910.00093/) (2019)
- [Feedback MPC for Torque-Controlled Legged Robots](https://mlsanity.com/paper/1905.06144/) (2019)
- [Whole-Body Nonlinear Model Predictive Control Through Contacts for Quadrupeds](https://mlsanity.com/paper/1712.02889/) (2017)
- [Automatic Differentiation of Rigid Body Dynamics for Optimal Control and Estimation](https://mlsanity.com/paper/1709.03799/) (2017)
- [Motion Planning for Quadrupedal Locomotion: Coupled Planning, Terrain Mapping and Whole-Body Control](https://mlsanity.com/paper/2003.05481/) (2020)
- [Real-Time Motion Planning of Legged Robots: A Model Predictive Control Approach](https://mlsanity.com/paper/1710.04029/) (2017)
- [Receding-Horizon Perceptive Trajectory Optimization for Dynamic Legged Locomotion with Learned Initialization](https://mlsanity.com/paper/2104.09078/) (2021)
- [Simultaneous Contact, Gait and Motion Planning for Robust Multi-Legged Locomotion via Mixed-Integer Convex Optimization](https://mlsanity.com/paper/1904.04595/) (2019)
- [Efficient Multi-Contact Pattern Generation with Sequential Convex Approximations of the Centroidal Dynamics](https://mlsanity.com/paper/2010.01215/) (2020)
- [Momentum Control with Hierarchical Inverse Dynamics on a Torque-Controlled Humanoid](https://mlsanity.com/paper/1410.7284/) (2014)
- [Stability of Surface Contacts for Humanoid Robots: Closed-Form Formulae of the Contact Wrench Cone for Rectangular Support Areas](https://mlsanity.com/paper/1501.04719/) (2015)
- [Structured contact force optimization for kino-dynamic motion generation](https://mlsanity.com/paper/1605.08571/) (2016)
- [Application of Wrench based Feasibility Analysis to the Online Trajectory Optimization of Legged Robots](https://mlsanity.com/paper/1712.06833/) (2017)
- [Model Predictive Control with Environment Adaptation for Legged Locomotion](https://mlsanity.com/paper/2105.05998/) (2021)
- [A Family of Iterative Gauss-Newton Shooting Methods for Nonlinear Optimal Control](https://mlsanity.com/paper/1711.11006/) (2017)
- [Passive Whole-body Control for Quadruped Robots: Experimental Validation over Challenging Terrain](https://mlsanity.com/paper/1811.00884/) (2018)
- [Constraint Handling in Continuous-Time DDP-Based Model Predictive Control](https://mlsanity.com/paper/2101.06067/) (2021)
- [A Convex Model of Momentum Dynamics for Multi-Contact Motion Generation](https://mlsanity.com/paper/1607.08644/) (2016)
- [Differential Dynamic Programming for Multi-Phase Rigid Contact Dynamics](https://mlsanity.com/paper/1904.05072/) (2019)
- [Solving Footstep Planning as a Feasibility Problem using L1-norm Minimization (Extended Version)](https://mlsanity.com/paper/2011.09772/) (2020)
- [Prioritized motion-force control of constrained fully-actuated robots: "Task Space Inverse Dynamics"](https://mlsanity.com/paper/1410.3863/) (2014)
- [SL1M: Sparse L1-norm Minimization for contact planning on uneven terrain](https://mlsanity.com/paper/1909.09044/) (2019)
- [Balancing experiments on a torque-controlled humanoid with hierarchical inverse dynamics](https://mlsanity.com/paper/1305.2042/) (2013)
- [Feasible Region: an Actuation-Aware Extension of the Support Region](https://mlsanity.com/paper/1903.07999/) (2019)
- [Hierarchical Planning of Dynamic Movements without Scheduled Contact Sequences](https://mlsanity.com/paper/1904.04600/) (2019)
- [Rapid Convex Optimization of Centroidal Dynamics using Block Coordinate Descent](https://mlsanity.com/paper/2108.01797/) (2021)
- [A Unified Model with Inertia Shaping for Highly Dynamic Jumps of Legged Robots](https://mlsanity.com/paper/2109.04581/) (2021)

## Built on by (most cited first, 8 of 8)

- [DTC: Deep Tracking Control](https://mlsanity.com/paper/2309.15462/) (2023)
- [Gaitor: Learning a Unified Representation Across Gaits for Real-World Quadruped Locomotion](https://mlsanity.com/paper/2405.19452/) (2024)
- [Guided Reinforcement Learning for Omnidirectional 3D Jumping in Quadruped Robots](https://mlsanity.com/paper/2507.16481/) (2025)
- [VAE-Loco: Versatile Quadruped Locomotion by Learning a Disentangled Gait Representation](https://mlsanity.com/paper/2205.01179/) (2022)
- [Efficient Reinforcement Learning for Jumping Monopods](https://mlsanity.com/paper/2309.07038/) (2023)
- [GeCCo -- a Generalist Contact-Conditioned Policy for Loco-Manipulation Skills on Legged Robots](https://mlsanity.com/paper/2509.17582/) (2025)
- [Elastic ODYN: Differentiable Optimization for Infeasible Control and Learning in Robotics](https://mlsanity.com/paper/2606.16564/) (2026)
- [CaLiSym: Learning Symplectic Dynamics of Real-World Systems through Structured Canonical Lifts](https://mlsanity.com/paper/2607.06824/) (2026)

## Abstract (arXiv)

Planning and execution of agile locomotion maneuvers have been a longstanding challenge in legged robotics. It requires to derive motion plans and local feedback policies in real-time to handle the nonholonomy of the kinetic momenta. To achieve so, we propose a hybrid predictive controller that considers the robot's actuation limits and full-body dynamics. It combines the feedback policies with tactile information to locally predict future actions. It converges within a few milliseconds thanks to a feasibility-driven approach. Our predictive controller enables ANYmal robots to generate agile maneuvers in realistic scenarios. A crucial element is to track the local feedback policies as, in contrast to whole-body control, they achieve the desired angular momentum. To the best of our knowledge, our predictive controller is the first to handle actuation limits, generate agile locomotion maneuvers, and execute optimal feedback policies for low level torque control without the use of a separate whole-body controller.