mlsanityData to 14 Oct 2026

Cognitively-Grounded On-Device Runtime Learning for Ground Robots in Unknown Physical Environments

arXiv 2608.28677 ↗First posted 25 Aug 2026cs.ROcited by 0

On the map: Deep reinforcement learning methods → Safe and constrained RL

Abstract (arXiv)

This paper presents ulCogRun, a framework that enables safety-critical ground robots to perform cognitively-grounded runtime learning entirely on edge-AI devices in unknown physical environments, without prior maps or perceptual knowledge. CogRun consists of three components: a Learning-Agent, a Rational-Agent, and a Coordinator. The Learning-Agent is novel in cognitive-neural learning architecture, which featurs dedicated replay buffers, cognition-driven experience sampling, and a safety-aware action blending of actor-critic reinforcement learning (RL) with instance-based learning (IBL). The Rational-Agent is a non-learning module that complements the Learning-Agent by exclusively handling safety-critical functions, while the Coordinator manages interactions between the two agents to promote safe and efficient runtime learning. CogRun's full autonomy stack (i.e., perception, learning, and control) on edge-AI devices eliminates dependence on wireless communications, enabling broader applications in challenging environments with limited or no connectivity. Experiments on a quadruped robot in real-world wild forests and on an off-road autonomous vehicle in a simulated wild forest demonstrate that CogRun enables safe and efficient runtime learning, allowing robots to safely and continuously interact with the physical world for enhancing task performance in complex, unknown environments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods. Builds on 22 of its 47 references that are in the map. First posted on arXiv 25 Aug 2026.

Builds on

22 of 47 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning22 May

Other references · 21

  1. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 319
  2. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 276
  3. 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 187
  4. 2022Rapid Locomotion via Reinforcement Learningcited by 168
  5. 2023ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robotscited by 152
  6. 2019Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systemscited by 78
  7. 2018Remember and Forget for Experience Replaycited by 43
  8. 2019Control Regularization for Reduced Variance Reinforcement Learningcited by 37
  9. 2022Safe Reinforcement Learning for Legged Locomotioncited by 35
  10. 2019Neural Simplex Architecturecited by 29
  11. 2021Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomizationcited by 23
  12. 2021Bayesian Controller Fusion: Leveraging Control Priors in Deep Reinforcement Learning for Roboticscited by 20
9 more
  1. 2023Physics-Regulated Deep Reinforcement Learning: Invariant Embeddingscited by 10
  2. 2020SL1-Simplex: Safe Velocity Regulation of Self-Driving Vehicles in Dynamic and Unforeseen Environmentscited by 9
  3. 2021Runtime Safety Assurance for Learning-enabled Control of Autonomous Driving Vehiclescited by 9
  4. 2022Equipping Black-Box Policies with Model-Based Advice for Stable Nonlinear Controlcited by 6
  5. 2022Cloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learningcited by 5
  6. 2023Lane-Keeping Control of Autonomous Vehicles Through a Soft-Constrained Iterative LQRcited by 4
  7. 2024Interactive-FAR:Interactive, Fast and Adaptable Routing for Navigation Among Movable Obstacles in Complex Unknown Environmentscited by 3
  8. 2025Sample Efficient Experience Replay in Non-stationary Environmentscited by 3
  9. 2024Demonstrating Reinforcement Learning and Run Time Assurance for Spacecraft Inspection Using Unmanned Aerial Vehiclescited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents
  2. 2025Cogito, Ergo Ludo: An Agent that Learns to Play by Reasoning and Planning
  3. 2021S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning
  4. 2024Environment as Policy: Learning to Race in Unseen Tracks
  5. 2025Real-DRL: Teach and Learn in Reality
  6. 2026Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement Learning
  7. 2026Cross-Embodiment Offline Reinforcement Learning for Heterogeneous Robot Datasets
  8. 2025World Models for Cognitive Agents: Transforming Edge Intelligence in Future Networks