Who to Trust in Multi-Robot Systems: Joint Robot and Object Hypothesis Trust Inference via Neural-Symbolic Cross-Validation

Ruiyang Wang; Hao-Lun Hsu; Haocheng Meng; Songqiao Xie; Miroslav Pajic

cs.ROOct 10, 2026

Who to Trust in Multi-Robot Systems: Joint Robot and Object Hypothesis Trust Inference via Neural-Symbolic Cross-Validation

Authors: Ruiyang Wang, Hao-Lun Hsu, Haocheng Meng, Songqiao Xie, Miroslav Pajic

Abstract

Multi-robot systems (MRS) offer significant advantages over single-robot platforms by enabling information sharing and coordination for different tasks in complex environments. However, reliable cooperation critically depends on inferring trust over both information sources and their reported hypotheses, particularly under partial observability and potential adversarial interference. Existing approaches frequently depend on pre-established trust relationships or side-channel information, which may not be available or reliable in realistic MRS deployments. This work introduces NeST-Bayes, a neural-symbolic framework that jointly infers robot and hypothesis trust using only inter-robot observation consistency, without requiring preassigned robot trust, reputation information, or side-channel identity signals. NeST-Bayes infers instantaneous trust evidence scores for robots and object hypotheses by reasoning over ego-centric relational graphs constructed from cross-robot observation consistency. These evidence scores are accumulated over time through Bayesian updates of Beta-distributed trust beliefs to maintain temporally consistent trust estimates. Extensive evaluations show that NeST-Bayes achieves the highest mean object precision and robot recall across all benchmark settings, and the highest robot precision and object recall in most settings, compared to trust-based methods. Under aggressive optimized attacks, it achieves 98.8% robot precision with 93.8% recall and 98.3% object precision with 95.4% recall. In an occlusion-rich Webots warehouse, it maintains 92.5% robot precision with 92.0% recall and 97.3% object precision with 85.0% recall. These results demonstrate joint improvements in the reliability and coverage of retained information.

Figures & tables

Fig. 1: NeST-Bayes pipeline: ego-centric graph construction, neural-symbolic evidence inference, and Bayesian evidence accumulation.

Relation Category	Edge Type	Condition & Interpretation
Robot–Track Relations (Sensing Consistency)
Observation	InFoV_Observed	A robot reports observing a fused track within its FoV.
Refutation	InFoV_Missed	A robot fails to observe a fused track within its FoV.
Robot–Robot Relations (Cross-Robot Consistency)
Consistency	Co-Detected	Both robots report observation of a fused track within their FoV.
Conflict	Contradicted	A robot reports observation that another robot refutes within its FoV.

TABLE I: Symbolic Edge Semantics in the Ego-Centric Graph

Fig. 2: Example simulation environment. Robots are shown as blue squares with shaded fields of view, ground-truth objects as green points, and false positive objects as red points.

Normal Adversarial Policy
Setting	Entity	Precision $\pm$ Std. / Recall $\pm$ Std. (%)
Setting	Entity	No Trust	Naïve Bayesian	MATE	NeST-Bayes
Nominal	Robot	$85.3{\pm}5.5/100.0{\pm}0.0$	$93.3{\pm}8.8/79.2{\pm}20.6$	$95.0{\pm}7.8/84.4{\pm}17.2$	$\mathbf{98.6{\pm}3.7/95.8{\pm}8.2}$
Nominal	Object	$83.3{\pm}5.5/100.0{\pm}0.0$	$94.7{\pm}7.4/95.1{\pm}10.9$	$95.0{\pm}7.5/87.1{\pm}11.4$	$\mathbf{98.0{\pm}5.0/93.7{\pm}8.4}$
High FP Injection $(\lambda_{\mathrm{FP}}^{a}\uparrow)$	Robot	$85.3{\pm}5.5/100.0{\pm}0.0$	$95.7{\pm}8.0/77.1{\pm}22.1$	$95.3{\pm}7.5/84.3{\pm}17.2$	$\mathbf{99.0{\pm}3.4/94.9{\pm}9.7}$
High FP Injection $(\lambda_{\mathrm{FP}}^{a}\uparrow)$	Object	$67.1{\pm}4.3/100.0{\pm}0.0$	$89.1{\pm}13.6/94.5{\pm}11.7$	$90.9{\pm}13.7/86.7{\pm}11.1$	$\mathbf{96.9{\pm}9.6/93.6{\pm}8.4}$

TABLE II: Precision and recall under normal and optimized adversarial policies. Each entry reports precision

\pm

standard deviation followed by recall

\pm

standard deviation, in percent. Each setting is evaluated over 100 independently generated scenarios.

Method	Precision / Recall (%)
Method	Robot	Object
No Trust	$84.7{\pm}5.4\,/\,100.0{\pm}0.0$	$86.2{\pm}5.4\,/\,100.0{\pm}0.0$
No Hetero GAT	$95.0{\pm}11.7\,/\,75.4{\pm}26.1$	$98.5{\pm}3.6\,/\,89.3{\pm}12.6$
Homogeneous GAT	$86.8{\pm}12.7\,/\,78.7{\pm}23.2$	$87.0{\pm}5.8\,/\,96.1{\pm}6.6$
Type Embeddings Only	$95.8{\pm}7.1\,/\,91.3{\pm}10.7$	$98.2{\pm}4.0\,/\,94.4{\pm}7.1$
NeST-Bayes (Full)	$\mathbf{97.2{\pm}6.2\,/\,95.5{\pm}8.8}$	$\mathbf{99.0{\pm}2.9\,/\,94.8{\pm}7.8}$

TABLE III: Component ablation over 100 comprehensive scenarios. Results are reported as mean

\pm

standard deviation.

Fig. 3: Webots warehouse simulation environment with five Spot robots and a mixture of objects. Occlusions from shelves and dynamic human agents create partial observability and asymmetric sensing among robots.

Method	Precision / Recall (%)
Method	Robot	Object
No Trust	$60.0{\pm}0.0\,/\,100.0{\pm}0.0$	$71.4{\pm}6.3\,/\,100.0{\pm}0.0$
Naïve Bayesian	$87.7{\pm}32.7\,/\,61.3{\pm}33.7$	$87.7{\pm}32.7\,/\,81.6{\pm}31.5$
MATE	$67.0{\pm}47.3\,/\,47.0{\pm}40.8$	$67.0{\pm}47.3\,/\,38.1{\pm}28.8$
NeST-Bayes (Ours)	$\mathbf{92.5{\pm}13.1\,/\,92.0{\pm}14.3}$	$\mathbf{97.3{\pm}5.4\,/\,85.0{\pm}7.5}$

TABLE IV: Precision and recall in the Webots simulations over 100 scenarios. Results are reported as mean

\pm

standard deviation.

Explore similar work

NeuroMesh: A Unified Neural Inference Framework for Decentralized Multi-Robot Collaboration
Apr 16, 2026Yang Zhou, Yash Shetye, Long Quang +8Efficient Neural Network Inference Multi-Robot Systems
New York University, New York, USA · U.S. Army Combat Capabilities Development Command, Army Research Laboratory, Adelphi, MD 20783, USA · Vanderbilt University, Tennessee, USA +1
Seeing is Not Believing: Breaking the Physical-to-Digital Trust Boundary in Robotics
Sep 8, 2026Leming Shen, Shikai Geng, Yuanqing Zheng +1Cybersecurity Software Security
University College London · The Hong Kong Polytechnic University
CoRelNav: Collaborative Relational Navigation for Multi-Robot Spatially Constrained Semantic Navigation
Sep 23, 2026Jinyu He, Zihao Mao, Haonan Jin +2Robot Navigation Multi-Robot Coordination
School of Automation, Beijing Institute of Technology, Beijing 100081, China

Apr 16, 2026J/K move · Enter open · S save

NeuroMesh: A Unified Neural Inference Framework for Decentralized Multi-Robot Collaboration

Yang Zhou, Yash Shetye, Long Quang, Devon Super+7

New York University, New York, USA · U.S. Army Combat Capabilities Development Command, Army Research Laboratory, Adelphi, MD 20783, USA · Vanderbilt University, Tennessee, USA+1

Efficient Neural Network Inference Multi-Robot Systems Multi-Robot Coordination Multi-Agent Communication Distributed Inference

Open paper AskPDF arXiv

Deploying learned multi-robot models on heterogeneous robots remains challenging due to hardware heterogeneity, communication constraints, and the lack of a unified execution stack. This paper presents NeuroMesh, a multi-domain, cross-platform, and modular decentralized neural inference framework that standardizes observation encoding, message passing, aggregation, and task decoding in a unified pipeline. NeuroMesh combines a dual-aggregation paradigm for reduction- and broadcast-based information fusion with a parallelized architecture that decouples cycle time from end-to-end latency. Our high-performance C++ implementation leverages Zenoh for inter-robot communication and supports hybrid GPU/CPU inference. We validate NeuroMesh on a heterogeneous team of aerial and ground robots across collaborative perception, decentralized control, and task assignment, demonstrating robust operation across diverse task structures and payload sizes. We plan to release NeuroMesh as an open-source framework to the community.

Abstract

Explore similar work

NeuroMesh: A Unified Neural Inference Framework for Decentralized Multi-Robot Collaboration

Seeing is Not Believing: Breaking the Physical-to-Digital Trust Boundary in Robotics

CoRelNav: Collaborative Relational Navigation for Multi-Robot Spatially Constrained Semantic Navigation