Evolving Skill Modules under a Fixed Planner: Versioning, Rollback, and Runtime Governance for Long-Lived Robot Systems

arXiv:2604.07799 · cs.RO, cs.AI · Submitted 2026-04-09 · Read on arXiv

cs.RO, cs.AI

Submitted: 2026-04-09

Updated: 2026-09-18

Comments: 66 pages, 6 figures, 12 tables. Submitted to the Journal of Systems and Software

Code: https://github.com/s20sc/capability-evolution

Project page: https://s20sc.github.io/aeros-project

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Reinforcement Learning — 11× in this paper · explained in 4 episodes
• Trace — 10× in this paper · explained in 2 episodes
• Agent Modification — 9× in this paper
• Embodied Capability Module — 6× in this paper
• Continual Learning — 4× in this paper · explained in 2 episodes
• Actor — 3× in this paper · explained in 3 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Core — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Abstraction — 2× in this paper · explained in 1 episode
• Action Space — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Conference on Robot Learning — 2× in this paper
• Modularity — 2× in this paper · explained in 9 episodes
• Prompt Engineering — 2× in this paper · explained in 4 episodes
• Affordance — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Deep Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Task Decomposition — 1× in this paper · explained in 2 episodes
• Temporal Abstraction — 1× in this paper · explained in 2 episodes

Sources

• AEROS: A Single-Agent Operating Architecture with Embodied Capability Modules
• robosuite: A Modular Simulation Framework and Benchmark for Robot Learning
• Progressive Neural Networks
• PathNet: Evolution Channels Gradient Descent in Super Neural Networks

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving