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

Apr 16, 2026

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

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.

Yang Zhou, Yash Shetye, Long Quang +8

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

Ask PDF

Sep 8, 2026

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

In multi-robot collaboration, task handovers rely on downstream verifiers performing remote attestation, which inspects sensor telemetry to ensure a robot's physical behavior strictly matches its assigned task. But can this telemetry be trusted? We show that it often cannot. In this paper, we uncover a severe vulnerability in Robot Operating System (ROS) 2: by modifying a single environment variable, an adversary can execute a pre-built hook to covertly intercept and inject both telemetry and control signals before they are published. Consequently, adversaries can hijack a robot to perform dangerous tasks while spoofing downstream verifiers with synthesized fake telemetry. Worse still, by exploiting the widespread reliance on third-party Docker containers and auxiliary tools, attackers can distribute compromised packages embedded with these malicious hooks to launch such attacks easily. On a physical Franka Emika robotic arm running Secure ROS 2, our attack injects fabricated telemetry in real time with only around 3 ms of jitter, preserving temporal synchronization and hardware integrity while achieving an 87% success rate even against an AI-based detector. We have responsibly disclosed these findings to the ROS 2 development team. We prepared a demo video available at https://youtu.be/ExeiGqUrnhQ.

Leming Shen, Shikai Geng, Yuanqing Zheng +1

University College London · The Hong Kong Polytechnic University

Cybersecurity Software Security Remote Attestation

Ask PDF

Sep 23, 2026

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

Spatially constrained semantic navigation requires robots to identify targets specified not only by semantic categories but also by relations to surrounding objects. In unknown environments, resolving such goals requires efficient exploration together with sufficient target and contextual evidence for reliable relation verification. Existing methods leave relation-aware verification and multi-robot collaboration largely disconnected: relational navigation is predominantly single-agent, while multi-robot systems seldom coordinate distributed observations for instance-specific relation verification. We propose CoRelNav, whose core is coupling task-conditioned multi-robot exploration with candidate-driven collaborative verification. A spatial-semantic field converts task constraints, scene nodes, and object features into exploration utility; as candidate information accumulates, robots are reallocated toward complementary evidence under team navigation costs, while instance-consistent observations are aggregated across topology nodes. This coupling reduces redundant search and enables relation hypotheses to be resolved from distributed partial evidence that independent exploration or isolated-view verification can leave ambiguous. Experiments in photorealistic simulation demonstrate consistent improvements over representative baselines, with ablations validating the proposed exploration and verification mechanisms. We further deploy the complete system on two physical mobile robots, demonstrating its applicability to real-world collaborative navigation.

Jinyu He, Zihao Mao, Haonan Jin +2

School of Automation, Beijing Institute of Technology, Beijing 100081, China

Robot Navigation Multi-Robot Coordination Multi-Robot Exploration Cooperative Perception

Ask PDF