arXiv subjects

Gregory Dudek

Publications and source records attributed to Gregory Dudek.

At least 19 recordsLinked to original sources

arXiv2026

Do LLMs Beat Nash? Testing Decentralized Coordination in Self-Play Multi-Agent Games

Large language model agents deployed without a central controller are often assumed to require communication to coordinate their actions. We ask what remains possible without it: when independent instances of the same model cannot communicate, can they still reason about their counterparts well enough to exceed the standard game-theoretic baseline for uncoordinated play? We introduce a benchmark of one-shot, no-communication games in which each of thirteen language models is told only that its counterparts are running the same model and is evaluated against the Nash equilibrium of the underlying game. In two-player matrix games spanning seven archetypes and two to ten actions per player, two frontier-hosted models consistently exceed their Nash benchmark, approaching the optimal joint outcome in several archetypes, while most open-weight models achieve only partial gains that vary sharply by game structure. Performance degrades substantially in team-based games with four or more interchangeable agents, particularly as the action space grows, suggesting that whatever capability drives self-play gains in dyadic games does not transfer to larger multi-agent teams.

cs.MA↗

arXiv2026

Tactile Modality Fusion for Vision-Language-Action Models

We propose TacFiLM, a lightweight modality-fusion approach that integrates visual-tactile signals into vision-language-action (VLA) models. While advances in VLAs have introduced robot policies that are both generalizable and semantically grounded, these models mainly rely on vision-based perception. Vision alone, however, cannot capture the complex interaction dynamics that occur during contact-rich manipulation, including contact forces, surface friction, compliance, and shear. While recent attempts to integrate tactile signals into VLA models often increase complexity through token concatenation or large-scale pretraining, the heavy computational demands of behaviour models necessitate lightweight fusion strategies. To address these challenges, TacFiLM outlines a post-training finetuning approach that conditions intermediate visual features on pretrained tactile representations using feature-wise linear modulation (FiLM). Experimental results on insertion and drawer opening tasks demonstrate consistent improvements in success rate, direct task performance, completion time, and force stability across both in-distribution and out-of-distribution tasks. Together, these results support our method as an effective approach to integrating tactile signals into VLA models, improving contact-rich manipulation behaviours. Project page: https://charliem7.github.io/projects/TacFilm/

cs.RO↗

arXiv2026

MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks

Real-world robotic tasks are long-horizon and often span multiple floors, demanding rich spatial reasoning. However, existing embodied benchmarks are largely confined to single-floor in-house environments, failing to reflect the complexity of real-world tasks. We introduce MANSION, the first language-driven framework for generating building-scale, multi-floor 3D environments. Being aware of vertical structural constraints, MANSION generates realistic, navigable whole-building structures with diverse, human-friendly scenes, enabling the development and evaluation of cross-floor long-horizon tasks. Building on this framework, we release MansionWorld, a dataset of over 1,000 diverse buildings ranging from hospitals to offices, alongside a Task-Semantic Scene Editing Agent that customizes these environments using open-vocabulary commands to meet specific user needs. Benchmarking reveals that state-of-the-art agents degrade sharply in our settings, establishing MANSION as a critical testbed for the next generation of spatial reasoning and planning.

cs.CV↗

arXiv2026

AMP2026: A Multi-Platform Marine Robotics Dataset for Tracking and Mapping

Marine environments present significant challenges for perception and autonomy due to dynamic surfaces, limited visibility, and complex interactions between aerial, surface, and submerged sensing modalities. This paper introduces the Aerial Marine Perception Dataset (AMP2026), a multi-platform marine robotics dataset collected across multiple field deployments designed to support research in two primary areas: multi-view tracking and marine environment mapping. The dataset includes synchronized data from aerial drones, boat-mounted cameras, and submerged robotic platforms, along with associated localization and telemetry information. The goal of this work is to provide a publicly available dataset enabling research in marine perception and multi-robot observation scenarios. This paper describes the data collection methodology, sensor configurations, dataset organization, and intended research tasks supported by the dataset.

cs.RO↗

arXiv2026

The Surprising Difficulty of Search in Model-Based Reinforcement Learning

This paper investigates search in model-based reinforcement learning (RL). Conventional wisdom holds that long-term predictions and compounding errors are the primary obstacles for model-based RL. We challenge this view, showing that search is not a drop-in replacement for a learned policy. Surprisingly, we find that search can harm performance even when the model is highly accurate. Instead, we show that mitigating overestimation bias matters more than improving model or value function accuracy. Building on this insight, we identify that taking the minimum over an ensemble of value functions effectively addresses this bias and enables effective search, achieving state-of-the-art performance across multiple popular benchmark domains.

cs.LG↗

arXiv2026

Contractive Diffusion Policies: Robust Action Diffusion via Contractive Score-Based Sampling with Differential Equations

Diffusion policies have emerged as powerful generative models for offline policy learning, whose sampling process can be rigorously characterized by a score function guiding a stochastic differential equation (SDE). However, the same score-based SDE modeling that grants diffusion policies the flexibility to learn diverse behavior also incurs solver and score-matching errors, large data requirements, and inconsistencies in action generation. While less critical in image generation, these inaccuracies compound and lead to failure in continuous control settings. We introduce contractive diffusion policies (CDPs) to induce contractive behavior in the diffusion sampling dynamics. Contraction pulls nearby flows closer to enhance robustness against solver and score-matching errors while reducing unwanted action variance. We develop an in-depth theoretical analysis along with a practical implementation recipe to incorporate CDPs into existing diffusion policy architectures with minimal modification and computational cost. We evaluate CDPs for offline learning by conducting extensive experiments in simulation and real-world settings. Across benchmarks, CDPs often outperform baseline policies, with pronounced benefits under data scarcity.

cs.LG↗

arXiv2025

On Mobile Ad Hoc Networks for Coverage of Partially Observable Worlds

This paper addresses the movement and placement of mobile agents to establish a communication network in initially unknown environments. We cast the problem in a computational-geometric framework by relating the coverage problem and line-of-sight constraints to the Cooperative Guard Art Gallery Problem, and introduce its partially observable variant, the Partially Observable Cooperative Guard Art Gallery Problem (POCGAGP). We then present two algorithms that solve POCGAGP: CADENCE, a centralized planner that incrementally selects 270 degree corners at which to deploy agents, and DADENCE, a decentralized scheme that coordinates agents using local information and lightweight messaging. Both approaches operate under partial observability and target simultaneous coverage and connectivity. We evaluate the methods in simulation across 1,500 test cases of varied size and structure, demonstrating consistent success in forming connected networks while covering and exploring unknown space. These results highlight the value of geometric abstractions for communication-driven exploration and show that decentralized policies are competitive with centralized performance while retaining scalability.

cs.RO↗

arXiv2025

Stable Multi-Drone GNSS Tracking System for Marine Robots

Stable and accurate tracking is essential for marine robotics, yet Global Navigation Satellite System (GNSS) signals vanish immediately below the sea surface. Traditional alternatives suffer from error accumulation, high computational demands, or infrastructure dependence. In this work, we present a multi-drone GNSS-based tracking system for surface and near-surface marine robots. Our approach combines efficient visual detection, lightweight multi-object tracking, GNSS-based triangulation, and a confidence-weighted Extended Kalman Filter (EKF) to provide stable GNSS estimation in real time. We further introduce a cross-drone tracking ID alignment algorithm that enforces global consistency across views, enabling robust multi-robot tracking with cooperative aerial coverage. We validate our system in diversified complex settings to show the accuracy and robustness of the proposed algorithm.

cs.RO↗

arXiv2025

Decentralized Multi-Agent Goal Assignment for Path Planning using Large Language Models

Coordinating multiple autonomous agents in shared environments under decentralized conditions is a long-standing challenge in robotics and artificial intelligence. This work addresses the problem of decentralized goal assignment for multi-agent path planning, where agents independently generate ranked preferences over goals based on structured representations of the environment, including grid visualizations and scenario data. After this reasoning phase, agents exchange their goal rankings, and assignments are determined by a fixed, deterministic conflict-resolution rule (e.g., agent index ordering), without negotiation or iterative coordination. We systematically compare greedy heuristics, optimal assignment, and large language model (LLM)-based agents in fully observable grid-world settings. Our results show that LLM-based agents, when provided with well-designed prompts and relevant quantitative information, can achieve near-optimal makespans and consistently outperform traditional heuristics. These findings underscore the potential of language models for decentralized goal assignment in multi-agent path planning and highlight the importance of information structure in such systems.

cs.AI↗

arXiv2025

Large Pre-Trained Models for Bimanual Manipulation in 3D

We investigate the integration of attention maps from a pre-trained Vision Transformer into voxel representations to enhance bimanual robotic manipulation. Specifically, we extract attention maps from DINOv2, a self-supervised ViT model, and interpret them as pixel-level saliency scores over RGB images. These maps are lifted into a 3D voxel grid, resulting in voxel-level semantic cues that are incorporated into a behavior cloning policy. When integrated into a state-of-the-art voxel-based policy, our attention-guided featurization yields an average absolute improvement of 8.2% and a relative gain of 21.9% across all tasks in the RLBench bimanual benchmark.

cs.CV↗

arXiv2025

Swarm Oracle: Trustless Blockchain Agreements through Robot Swarms

Blockchain consensus, rooted in the principle ``don't trust, verify'', limits access to real-world data, which may be ambiguous or inaccessible to some participants. Oracles address this limitation by supplying data to blockchains, but existing solutions may reduce autonomy, transparency, or reintroduce the need for trust. We propose Swarm Oracle: a decentralized network of autonomous robots -- that is, a robot swarm -- that use onboard sensors and peer-to-peer communication to collectively verify real-world data and provide it to smart contracts on public blockchains. Swarm Oracle leverages the built-in decentralization, fault tolerance and mobility of robot swarms, which can flexibly adapt to meet information requests on-demand, even in remote locations. Unlike typical cooperative robot swarms, Swarm Oracle integrates robots from multiple stakeholders, protecting the system from single-party biases but also introducing potential adversarial behavior. To ensure the secure, trustless and global consensus required by blockchains, we employ a Byzantine fault-tolerant protocol that enables robots from different stakeholders to operate together, reaching social agreements of higher quality than the estimates of individual robots. Through extensive experiments using both real and simulated robots, we showcase how consensus on uncertain environmental information can be achieved, despite several types of attacks orchestrated by large proportions of the robots, and how a reputation system based on blockchain tokens lets Swarm Oracle autonomously recover from faults and attacks, a requirement for long-term operation.

cs.RO↗

arXiv2025

Scalable Aerial GNSS Localization for Marine Robots

Accurate localization is crucial for water robotics, yet traditional onboard Global Navigation Satellite System (GNSS) approaches are difficult or ineffective due to signal reflection on the water's surface and its high cost of aquatic GNSS receivers. Existing approaches, such as inertial navigation, Doppler Velocity Loggers (DVL), SLAM, and acoustic-based methods, face challenges like error accumulation and high computational complexity. Therefore, a more efficient and scalable solution remains necessary. This paper proposes an alternative approach that leverages an aerial drone equipped with GNSS localization to track and localize a marine robot once it is near the surface of the water. Our results show that this novel adaptation enables accurate single and multi-robot marine robot localization.

cs.RO↗

arXiv2024

Learning Heuristics for Transit Network Design and Improvement with Deep Reinforcement Learning

Planning a network of public transit routes is a challenging optimization problem. Metaheuristic algorithms search through the space of possible transit networks by applying heuristics that randomly alter routes in a network. Existing algorithms almost exclusively use heuristics that modify the network in purely random ways. In this work, we explore whether we can obtain better transit networks using more intelligent heuristics, that modify networks according to a learned preference function instead of at random. We use reinforcement learning to train graph neural nets to act as heuristics. These neural heuristics yield improved results on benchmark synthetic cities with 70 nodes or more, and achieve new state-of-the-art results on the challenging Mumford benchmark. They also improve upon a simulation of the real transit network in the city of Laval, Canada, achieving cost savings of up to 19% over the city's existing transit network.

cs.LG↗

arXiv2024

Constrained Robotic Navigation on Preferred Terrains Using LLMs and Speech Instruction: Exploiting the Power of Adverbs

This paper explores leveraging large language models for map-free off-road navigation using generative AI, reducing the need for traditional data collection and annotation. We propose a method where a robot receives verbal instructions, converted to text through Whisper, and a large language model (LLM) model extracts landmarks, preferred terrains, and crucial adverbs translated into speed settings for constrained navigation. A language-driven semantic segmentation model generates text-based masks for identifying landmarks and terrain types in images. By translating 2D image points to the vehicle's motion plane using camera parameters, an MPC controller can guides the vehicle towards the desired terrain. This approach enhances adaptation to diverse environments and facilitates the use of high-level instructions for navigating complex and challenging terrains.

cs.RO↗

arXiv2024

A Neural-Evolutionary Algorithm for Autonomous Transit Network Design

Planning a public transit network is a challenging optimization problem, but essential in order to realize the benefits of autonomous buses. We propose a novel algorithm for planning networks of routes for autonomous buses. We first train a graph neural net model as a policy for constructing route networks, and then use the policy as one of several mutation operators in a evolutionary algorithm. We evaluate this algorithm on a standard set of benchmarks for transit network design, and find that it outperforms the learned policy alone by up to 20% and a plain evolutionary algorithm approach by up to 53% on realistic benchmark instances.

cs.NE↗

arXiv2024

A comparison of RL-based and PID controllers for 6-DOF swimming robots: hybrid underwater object tracking

In this paper, we present an exploration and assessment of employing a centralized deep Q-network (DQN) controller as a substitute for the prevalent use of PID controllers in the context of 6DOF swimming robots. Our primary focus centers on illustrating this transition with the specific case of underwater object tracking. DQN offers advantages such as data efficiency and off-policy learning, while remaining simpler to implement than other reinforcement learning methods. Given the absence of a dynamic model for our robot, we propose an RL agent to control this multi-input-multi-output (MIMO) system, where a centralized controller may offer more robust control than distinct PIDs. Our approach involves initially using classical controllers for safe exploration, then gradually shifting to DQN to take full control of the robot. We divide the underwater tracking task into vision and control modules. We use established methods for vision-based tracking and introduce a centralized DQN controller. By transmitting bounding box data from the vision module to the control module, we enable adaptation to various objects and effortless vision system replacement. Furthermore, dealing with low-dimensional data facilitates cost-effective online learning for the controller. Our experiments, conducted within a Unity-based simulator, validate the effectiveness of a centralized RL agent over separated PID controllers, showcasing the applicability of our framework for training the underwater RL agent and improved performance compared to traditional control methods. The code for both real and simulation implementations is at https://github.com/FARAZLOTFI/underwater-object-tracking.

cs.RO↗

arXiv2024

Probabilistic Mobility Load Balancing for Multi-band 5G and Beyond Networks

The ever-increasing demand for data services and the proliferation of user equipment (UE) have resulted in a significant rise in the volume of mobile traffic. Moreover, in multi-band networks, non-uniform traffic distribution among different operational bands can lead to congestion, which can adversely impact the user's quality of experience. Load balancing is a critical aspect of network optimization, where it ensures that the traffic is evenly distributed among different bands, avoiding congestion and ensuring better user experience. Traditional load balancing approaches rely only on the band channel quality as a load indicator and to move UEs between bands, which disregards the UE's demands and the band resource, and hence, leading to a suboptimal balancing and utilization of resources. To address this challenge, we propose an event-based algorithm, in which we model the load balancing problem as a multi-objective stochastic optimization, and assign UEs to bands in a probabilistic manner. The goal is to evenly distribute traffic across available bands according to their resources, while maintaining minimal number of inter-frequency handovers to avoid the signaling overhead and the interruption time. Simulation results show that the proposed algorithm enhances the network's performance and outperforms traditional load balancing approaches in terms of throughput and interruption time.

cs.NI↗

arXiv2024

PhotoBot: Reference-Guided Interactive Photography via Natural Language

We introduce PhotoBot, a framework for fully automated photo acquisition based on an interplay between high-level human language guidance and a robot photographer. We propose to communicate photography suggestions to the user via reference images that are selected from a curated gallery. We leverage a visual language model (VLM) and an object detector to characterize the reference images via textual descriptions and then use a large language model (LLM) to retrieve relevant reference images based on a user's language query through text-based reasoning. To correspond the reference image and the observed scene, we exploit pre-trained features from a vision transformer capable of capturing semantic similarity across marked appearance variations. Using these features, we compute suggested pose adjustments for an RGB-D camera by solving a perspective-n-point (PnP) problem. We demonstrate our approach using a manipulator equipped with a wrist camera. Our user studies show that photos taken by PhotoBot are often more aesthetically pleasing than those taken by users themselves, as measured by human feedback. We also show that PhotoBot can generalize to other reference sources such as paintings.

cs.CV↗