High-Level Multi-Robot Trajectory Planning And Spurious Behavior Detection

arXiv cs.RO / 4/23/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper tackles robust detection of “spurious” multi-robot plan executions, including wrong task orders, spatial-constraint violations, timing inconsistencies, and semantic deviations from LTL-specified missions.
It introduces a structured data generation framework using the Nets-within-Nets (NWN) paradigm to coordinate robot actions with global mission constraints derived from Linear Temporal Logic (LTL) formulas.
The authors propose a Transformer-based anomaly detection pipeline that classifies robot trajectories as normal or anomalous based on learned patterns.
Experiments report strong performance, including 91.3% accuracy for execution inefficiencies and 88.3% detection for core mission violations, while adaptive constraint anomalies are detected at 66.8%.
An ablation study on embeddings and architecture supports that the proposed representation/approach outperforms simpler alternatives.

Abstract

The reliable execution of high-level missions in multi-robot systems with heterogeneous agents, requires robust methods for detecting spurious behaviors. In this paper, we address the challenge of identifying spurious executions of plans specified as a Linear Temporal Logic (LTL) formula, as incorrect task sequences, violations of spatial constraints, timing inconsistencies, or deviations from intended mission semantics. To tackle this, we introduce a structured data generation framework based on the Nets-within-Nets (NWN) paradigm, which coordinates robot actions with LTL-derived global mission specifications. We further propose a Transformer-based anomaly detection pipeline that classifies robot trajectories as normal or anomalous. Experimental evaluations show that our method achieves high accuracy (91.3%) in identifying execution inefficiencies, and demonstrates robust detection capabilities for core mission violations (88.3%) and constraint-based adaptive anomalies (66.8%). An ablation experiment of the embedding and architecture was carried out, obtaining successful results where our novel proposition performs better than simpler representations.