EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Toward edge-intelligent consumer robots: a decoupled RL–LLM architecture for robust navigation under partial observability

Yule Cai, Wang Tan, Yichen Wang, Xinke Du, Tao Sun, Qian Ai, Sami Bourouis, Shiyam Alalmaei, Wenbin Shao, Chunhong Yuan

Journal of King Saud University Computer and Information Sciences · 2026-08 · 38 (6)

DOI: 10.1007/s44443-026-00870-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of King Saud University Computer and Information Sciences, online erschienen am 01.06.2026. Verfasst von Yule Cai und 9 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Victoria University of Wellington.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid proliferation of GPU-free consumer edge robots—including household service units, smart vacuum cleaners, and autonomous indoor logistics platforms—demands navigation intelligence capable of operating under strict on-device computational constraints and severely limited perceptual access. Existing approaches suffer from a fundamental dichotomy: classical local planners achieve near-perfect success rates but require exhaustive internal state bookkeeping incompatible with stateless embedded execution, whereas neural reinforcement learning (RL) agents exhibit efficient perception–action loops yet catastrophically fail in non-convex obstacle fields through an overconfidence trap—a confident but physically stuck state invisible to conventional policy-entropy-based monitors. We present a decoupled RL–LLM dual-brain co-navigation framework that provides a computationally efficient representation for the cognitive planning tier of ARM-class consumer edge robots. Three tightly integrated innovations drive the system: (i) a black-box spatio-temporal stuck detector based solely on physical displacement monitoring, which consistently detects the overconfidence trap that entropy triggers miss; (ii) an ASCII topology serialisation interface that maps local radar observations to structured text grids natively aligned with the pretraining priors of code-specialised small language models, decoupling the cognitive tier from continuous low-level controllers; and (iii) a bottom-up fault-tolerant architecture augmented by a Trap Repulsion Field, wherein the RL physical layer absorbs top-level large language model (LLM) spatial hallucinations, enabling system-level robustness without requiring an infallible oracle. Evaluated across five difficulty levels against seven baselines—including artificial potential fields (APF), Pure Deep Q-Network (DQN), pure Proximal Policy Optimisation (PPO), and three local graph-search methods—over 50 independent start–goal episodes per level (1,750 total evaluations), our framework achieves the highest success rate among all learning-based and reactive methods at 95% averaged across all levels, versus 72% for pure PPO, 9% for pure DQN, and 5% for APF, with a mean path cost of 50 steps on successful episodes. An edge deployment experiment on an Orange Pi board with a locally hosted 1.2B-parameter LLM (LFM-2.5) confirms 90% success on the hardest map with a mean inference latency of 37.82 s per call, establishing the viability of on-device cognitive-tier planning on mass-market, GPU-free consumer hardware.

Förderung

  • Victoria University of Wellington

Zitieren

APA

Cai, Y., Tan, W., Wang, Y., Du, X., Sun, T., Ai, Q., Bourouis, S., Alalmaei, S., Shao, W., & Yuan, C. (2026). Toward edge-intelligent consumer robots: a decoupled RL–LLM architecture for robust navigation under partial observability. Journal of King Saud University Computer and Information Sciences, 38(6). https://doi.org/10.1007/s44443-026-00870-9

Vancouver

Cai Y, Tan W, Wang Y, Du X, Sun T, Ai Q, et al. Toward edge-intelligent consumer robots: a decoupled RL–LLM architecture for robust navigation under partial observability. Journal of King Saud University Computer and Information Sciences. 2026;38(6). doi:10.1007/s44443-026-00870-9

BibTeX
@article{Cai2026,
  author = {Cai, Yule and Tan, Wang and Wang, Yichen and Du, Xinke and Sun, Tao and Ai, Qian and Bourouis, Sami and Alalmaei, Shiyam and Shao, Wenbin and Yuan, Chunhong},
  title = {Toward edge-intelligent consumer robots: a decoupled RL–LLM architecture for robust navigation under partial observability},
  journal = {Journal of King Saud University Computer and Information Sciences},
  year = {2026},
  volume = {38},
  number = {6},
  doi = {10.1007/s44443-026-00870-9}
}
Kostenlos starten →