Position: Towards a Responsible LLM-empowered Multi-Agent Systems

The rise of Agent AI and Large Language Model-powered Multi-Agent Systems (LLM-MAS) has underscored the need for responsible and dependable system operation. Tools like LangChain and Retrieval-Augmented Generation have expanded LLM capabilities, enabling deeper integration into MAS through enhanced knowledge retrieval and reasoning. However, these advancements introduce critical challenges: LLM agents exhibit inherent unpredictability, and uncertainties in their outputs can compound across interactions, threatening system stability. To address these risks, a human-centered design approach with active dynamic moderation is essential. Such an approach enhances traditional passive oversight by facilitating coherent inter-agent communication and effective system governance, allowing MAS to achieve desired outcomes more efficiently.

Image-based Geo-localization for Robotics: Are Black-box Vision-Language Models there yet?

The advances in Vision-Language models (VLMs) offer exciting opportunities for robotic applications involving image geo-localization, the problem of identifying the geo-coordinates of a place based on visual data only. Recent research works have focused on using a VLM as embeddings extractor for geo-localization, however, the most sophisticated VLMs may only be available as black boxes that are accessible through an API, and come with a number of limitations: there is no access to training data, model features and gradients; retraining is not possible; the number of predictions may be limited by the API; training on model outputs is often prohibited; and queries are open-ended. The utilization of a VLM as a stand-alone, zero-shot geo-localization system using a single text-based prompt is largely unexplored. To bridge this gap, this paper undertakes the first systematic study, to the best of our knowledge, to investigate the potential of some of the state-of-the-art VLMs as stand-alone, zero-shot geo-localization systems in a black-box setting with realistic constraints. We consider three main scenarios for this thorough investigation: a) fixed text-based prompt; b) semantically-equivalent text-based prompts; and c) semantically-equivalent query images. We also take into account the auto-regressive and probabilistic generation process of the VLMs when investigating their utility for geo-localization task by using model consistency as a metric in addition to traditional accuracy. Our work provides new insights in the capabilities of different VLMs for the above-mentioned scenarios.

Structured Pruning for Efficient Visual Place Recognition

Visual Place Recognition (VPR) is fundamental for the global re-localization of robots and devices, enabling them to recognize previously visited locations based on visual inputs. This capability is crucial for maintaining accurate mapping and localization over large areas. Given that VPR methods need to operate in real-time on embedded systems, it is critical to optimize these systems for minimal resource consumption. While the most efficient VPR approaches employ standard convolutional backbones with fixed descriptor dimensions, these often lead to redundancy in the embedding space as well as in the network architecture. Our work introduces a novel structured pruning method, to not only streamline common VPR architectures but also to strategically remove redundancies within the feature embedding space. This dual focus significantly enhances the efficiency of the system, reducing both map and model memory requirements and decreasing feature extraction and retrieval latencies. Our approach has reduced memory usage and latency by 21% and 16%, respectively, across models, while minimally impacting recall@1 accuracy by less than 1%. This significant improvement enhances real-time applications on edge devices with negligible accuracy loss.

Mapping Safe Zones for Co-located Human-UAV Interaction

Recent advances in robotics bring us closer to the reality of living, co-habiting, and sharing personal spaces with robots. However, it is not clear how close a co-located robot can be to a human in a shared environment without making the human uncomfortable or anxious. This research aims to map safe and comfortable zones for co-located aerial robots. The objective is to identify the distances at which a drone causes discomfort to a co-located human and to create a map showing no-fly, moderate-fly, and safe-fly zones. We recruited a total of 18 participants and conducted two indoor laboratory experiments, one with a single drone and the other set with two drones. Our results show that multiple drones cause more discomfort when close to a co-located human than a single drone. We observed that distances below 200 cm caused discomfort, the moderate fly zone was 200 - 300 cm, and the safe-fly zone was any distance greater than 300 cm in single drone experiments. The safe zones were pushed further away by 100 cm for the multiple drone experiments. In this paper, we present the preliminary findings on safe-fly zones for multiple drones. Further work would investigate the impact of a higher number of aerial robots, the speed of approach, direction of travel, and noise level on co-located humans, and autonomously develop 3D models of trust zones and safe zones for co-located aerial swarms.

Trade-offs of Dynamic Control Structure in Human-swarm Systems

Swarm robotics is a study of simple robots that exhibit complex behaviour only by interacting locally with other robots and their environment. The control in swarm robotics is mainly distributed whereas centralised control is widely used in other fields of robotics. Centralised and decentralised control strategies both pose a unique set of benefits and drawbacks for the control of multi-robot systems. While decentralised systems are more scalable and resilient, they are less efficient compared to the centralised systems and they lead to excessive data transmissions to the human operators causing cognitive overload. We examine the trade-offs of each of these approaches in a human-swarm system to perform an environmental monitoring task and propose a flexible hybrid approach, which combines elements of hierarchical and decentralised systems. We find that a flexible hybrid system can outperform a centralised system (in our environmental monitoring task by 19.2%) while reducing the number of messages sent to a human operator (here by 23.1%). We conclude that establishing centralisation for a system is not always optimal for performance and that utilising aspects of centralised and decentralised systems can keep the swarm from hindering its performance.

Learning to Imitate Spatial Organization in Multi-robot Systems

Understanding collective behavior and how it evolves is important to ensure that robot swarms can be trusted in a shared environment. One way to understand the behavior of the swarm is through collective behavior reconstruction using prior demonstrations. Existing approaches often require access to the swarm controller which may not be available. We reconstruct collective behaviors in distinct swarm scenarios involving shared environments without using swarm controller information. We achieve this by transforming prior demonstrations into features that sufficiently describe multi-agent interactions before behavior reconstruction with multi-agent generative adversarial imitation learning (MA-GAIL). We show that our approach outperforms existing algorithms in all investigated swarm scenarios, and can be used to observe and reconstruct a swarm's behavior for further analysis and testing, which might be impractical or undesirable on the original robot swarm.

A Survey of Language-Based Communication in Robotics

Embodied robots which can interact with their environment and neighbours are increasingly being used as a test case to develop Artificial Intelligence. This creates a need for multimodal robot controllers which can operate across different types of information including text. Large Language Models are able to process and generate textual as well as audiovisual data and, more recently, robot actions. Language Models are increasingly being applied to robotic systems; these Language-Based robots leverage the power of language models in a variety of ways. Additionally, the use of language opens up multiple forms of information exchange between members of a human-robot team. This survey motivates the use of language models in robotics, and then delineates works based on the part of the overall control flow in which language is incorporated. Language can be used by human to task a robot, by a robot to inform a human, between robots as a human-like communication medium, and internally for a robot's planning and control. Applications of language-based robots are explored, and finally numerous limitations and challenges are discussed to provide a summary of the development needed for language-based robotics moving forward. Links to each paper and, if available, source code are made available in the accompanying site at https://uos-haris.online/sooratilab/papers/WillSurvey/LangRobotSurvey.php

Adaptive Human-Swarm Interaction based on Workload Measurement using Functional Near-Infrared Spectroscopy

One of the challenges of human-swarm interaction (HSI) is how to manage the operator's workload. In order to do this, we propose a novel neurofeedback technique for the real-time measurement of workload using functional near-infrared spectroscopy (fNIRS). The objective is to develop a baseline for workload measurement in human-swarm interaction using fNIRS and to develop an interface that dynamically adapts to the operator's workload. The proposed method consists of using fNIRS device to measure brain activity, process this through a machine learning algorithm, and pass it on to the HSI interface. By dynamically adapting the HSI interface, the swarm operator's workload could be reduced and the performance improved.

The Strain of Success: A Predictive Model for Injury Risk Mitigation and Team Success in Soccer

In this paper, we present a novel sequential team selection model in soccer. Specifically, we model the stochastic process of player injury and unavailability using player-specific information learned from real-world soccer data. Monte-Carlo Tree Search is used to select teams for games that optimise long-term team performance across a soccer season by reasoning over player injury probability. We validate our approach compared to benchmark solutions for the 2018/19 English Premier League season. Our model achieves similar season expected points to the benchmark whilst reducing first-team injuries by ~13% and the money inefficiently spent on injured players by ~11% - demonstrating the potential to reduce costs and improve player welfare in real-world soccer teams.

The Effect of Predictive Formal Modelling at Runtime on Performance in Human-Swarm Interaction

Formal Modelling is often used as part of the design and testing process of software development to ensure that components operate within suitable bounds even in unexpected circumstances. In this paper, we use predictive formal modelling (PFM) at runtime in a human-swarm mission and show that this integration can be used to improve the performance of human-swarm teams. We recruited 60 participants to operate a simulated aerial swarm to deliver parcels to target locations. In the PFM condition, operators were informed of the estimated completion times given the number of drones deployed, whereas in the No-PFM condition, operators did not have this information. The operators could control the mission by adding or removing drones from the mission and thereby, increasing or decreasing the overall mission cost. The evaluation of human-swarm performance relied on four key metrics: the time taken to complete tasks, the number of agents involved, the total number of tasks accomplished, and the overall cost associated with the human-swarm task. Our results show that PFM modelling at runtime improves mission performance without significantly affecting the operator's workload or the system's usability.