# Learning Directed Locomotion in Modular Robots with Evolvable Morphologies

arXiv: https://arxiv.org/abs/2001.07804 · HTML: https://mlsanity.com/paper/2001.07804/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jan 2020.

## Built on by (most cited first, 19 of 19)

- [Class Binarization to NeuroEvolution for Multiclass Classification](https://mlsanity.com/paper/2308.13876/) (2023)
- [MORPH: Design Co-optimization with Reinforcement Learning via a Differentiable Hardware Model Proxy](https://mlsanity.com/paper/2309.17227/) (2023)
- [Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges](https://mlsanity.com/paper/2512.04770/) (2025)
- [Intelligent Perception System for Vehicle-Road Cooperation](https://mlsanity.com/paper/2208.14052/) (2022)
- [Active Data Acquisition in Autonomous Driving Simulation](https://mlsanity.com/paper/2306.13923/) (2023)
- [Deep learning for 3D Object Detection and Tracking in Autonomous Driving: A Brief Survey](https://mlsanity.com/paper/2311.06043/) (2023)
- [Automatic parking planning control method based on improved A* algorithm](https://mlsanity.com/paper/2406.15429/) (2024)
- [Quality and Computation Time in Optimization Problems](https://mlsanity.com/paper/2111.10595/) (2021)
- [Vehicle-road Cooperative Simulation and 3D Visualization System](https://mlsanity.com/paper/2208.07304/) (2022)
- [PCG-based Static Underground Garage Scenario Generation](https://mlsanity.com/paper/2307.03988/) (2023)
- [Real-time pedestrian recognition on low computational resources](https://mlsanity.com/paper/2309.01353/) (2023)
- [Automated Parking Planning with Vision-Based BEV Approach](https://mlsanity.com/paper/2406.15430/) (2024)
- [Acceleration method for generating perception failure scenarios based on editing Markov process](https://mlsanity.com/paper/2407.00980/) (2024)
- [Deep Reinforcement Learning for Adverse Garage Scenario Generation](https://mlsanity.com/paper/2407.01333/) (2024)
- [Research on Reliable and Safe Occupancy Grid Prediction in Underground Parking Lots](https://mlsanity.com/paper/2407.02197/) (2024)
- [Development of Occupancy Prediction Algorithm for Underground Parking Lots](https://mlsanity.com/paper/2409.00923/) (2024)
- [More complex environments may be required to discover benefits of lifetime learning in evolving robots](https://mlsanity.com/paper/2412.16184/) (2024)
- [Manboformer: Learning Gaussian Representations via Spatial-temporal Attention Mechanism](https://mlsanity.com/paper/2503.04863/) (2025)
- [Lamarckian Inheritance in Dynamic Environments: How Key Variables Affect Evolutionary Dynamics](https://mlsanity.com/paper/2605.15769/) (2026)

## Abstract (arXiv)

We generalize the well-studied problem of gait learning in modular robots in two dimensions. Firstly, we address locomotion in a given target direction that goes beyond learning a typical undirected gait. Secondly, rather than studying one fixed robot morphology we consider a test suite of different modular robots. This study is based on our interest in evolutionary robot systems where both morphologies and controllers evolve. In such a system, newborn robots have to learn to control their own body that is a random combination of the bodies of the parents. We apply and compare two learning algorithms, Bayesian optimization and HyperNEAT. The results of the experiments in simulation show that both methods successfully learn good controllers, but Bayesian optimization is more effective and efficient. We validate the best learned controllers by constructing three robots from the test suite in the real world and observe their fitness and actual trajectories. The obtained results indicate a reality gap that depends on the controllers and the shape of the robots, but overall the trajectories are adequate and follow the target directions successfully.