# DeepTransition: Viability Leads to the Emergence of Gait Transitions in Learning Anticipatory Quadrupedal Locomotion Skills

arXiv: https://arxiv.org/abs/2306.07419 · HTML: https://mlsanity.com/paper/2306.07419/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 80 references that are in the map.
- First posted on arXiv 12 Jun 2023.

## Builds on (most cited first, 27 of 27)

- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [Legged Locomotion in Challenging Terrains using Egocentric Vision](https://mlsanity.com/paper/2211.07638/) (2022)
- [Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robots](https://mlsanity.com/paper/2111.01674/) (2021)
- [Fast and Efficient Locomotion via Learned Gait Transitions](https://mlsanity.com/paper/2104.04644/) (2021)
- [Advanced Skills by Learning Locomotion and Local Navigation End-to-End](https://mlsanity.com/paper/2209.12827/) (2022)
- [Learning to Jump from Pixels](https://mlsanity.com/paper/2110.15344/) (2021)
- [Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations](https://mlsanity.com/paper/2206.11693/) (2022)
- [Neural Volumetric Memory for Visual Locomotion Control](https://mlsanity.com/paper/2304.01201/) (2023)
- [Barkour: Benchmarking Animal-level Agility with Quadruped Robots](https://mlsanity.com/paper/2305.14654/) (2023)
- [OPT-Mimic: Imitation of Optimized Trajectories for Dynamic Quadruped Behaviors](https://mlsanity.com/paper/2210.01247/) (2022)
- [CPG-RL: Learning Central Pattern Generators for Quadruped Locomotion](https://mlsanity.com/paper/2211.00458/) (2022)
- [Learning and Adapting Agile Locomotion Skills by Transferring Experience](https://mlsanity.com/paper/2304.09834/) (2023)
- [Learning Free Gait Transition for Quadruped Robots via Phase-Guided Controller](https://mlsanity.com/paper/2201.00206/) (2022)
- [RL + Model-based Control: Using On-demand Optimal Control to Learn Versatile Legged Locomotion](https://mlsanity.com/paper/2305.17842/) (2023)
- [GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model](https://mlsanity.com/paper/2104.09771/) (2021)
- [Robust High-speed Running for Quadruped Robots via Deep Reinforcement Learning](https://mlsanity.com/paper/2103.06484/) (2021)
- [Vision-aided Dynamic Quadrupedal Locomotion on Discrete Terrain using Motion Libraries](https://mlsanity.com/paper/2110.00891/) (2021)
- [Fast and Continuous Foothold Adaptation for Dynamic Locomotion through CNNs](https://mlsanity.com/paper/1809.09759/) (2018)
- [PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations](https://mlsanity.com/paper/2207.13224/) (2022)
- [Versatile modular neural locomotion control with fast learning](https://mlsanity.com/paper/2107.07844/) (2021)
- [Puppeteer and Marionette: Learning Anticipatory Quadrupedal Locomotion Based on Interactions of a Central Pattern Generator and Supraspinal Drive](https://mlsanity.com/paper/2302.13378/) (2023)
- [Robust walking based on MPC with viability guarantees](https://mlsanity.com/paper/2010.04514/) (2020)
- [Beyond Basins of Attraction: Quantifying Robustness of Natural Dynamics](https://mlsanity.com/paper/1806.08081/) (2018)
- [Online DCM Trajectory Generation for Push Recovery of Torque-Controlled Humanoid Robots](https://mlsanity.com/paper/1909.10403/) (2019)
- [An energy landscape approach to locomotor transitions in complex 3D terrain](https://mlsanity.com/paper/2006.12717/) (2020)

## Built on by (most cited first, 2 of 2)

- [ManyQuadrupeds: Learning a Single Locomotion Policy for Diverse Quadruped Robots](https://mlsanity.com/paper/2310.10486/) (2023)
- [FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning](https://mlsanity.com/paper/2402.13820/) (2024)

## Abstract (arXiv)

Quadruped animals seamlessly transition between gaits as they change locomotion speeds. While the most widely accepted explanation for gait transitions is energy efficiency, there is no clear consensus on the determining factor, nor on the potential effects from terrain properties. In this article, we propose that viability, i.e. the avoidance of falls, represents an important criterion for gait transitions. We investigate the emergence of gait transitions through the interaction between supraspinal drive (brain), the central pattern generator in the spinal cord, the body, and exteroceptive sensing by leveraging deep reinforcement learning and robotics tools. Consistent with quadruped animal data, we show that the walk-trot gait transition for quadruped robots on flat terrain improves both viability and energy efficiency. Furthermore, we investigate the effects of discrete terrain (i.e. crossing successive gaps) on imposing gait transitions, and find the emergence of trot-pronk transitions to avoid non-viable states. Compared with other potential criteria such as peak forces and energy efficiency, viability is the only improved factor after gait transitions on both flat and discrete gap terrains, suggesting that viability could be a primary and universal objective of gait transitions, while other criteria are secondary objectives and/or a consequence of viability. Moreover, we deploy our learned controller in sim-to-real hardware experiments and demonstrate state-of-the-art quadruped agility in challenging scenarios, where the Unitree A1 quadruped autonomously transitions gaits between trot and pronk to cross consecutive gaps of up to 30 cm (83.3 % of the body-length) at over 1.3 m/s.