We propose MAP-NBV, a prediction-guided active algorithm for 3D reconstruction with multi-agent systems. Prediction-based approaches have shown great improvement in active perception tasks by learning the cues about structures in the environment from data. But these methods primarily focus on single-agent systems. We design a next-best-view approach that utilizes geometric measures over the predictions and jointly optimizes the information gain and control effort for efficient collaborative 3D reconstruction of the object. Our method achieves 22.75% improvement over the prediction-based single-agent approach and 15.63% improvement over the non-predictive multi-agent approach. We make our code publicly available through our project website: http://raaslab.org/projects/MAPNBV/

Large-scale systems where agents interact competitively with each other have received significant attention recently, motivated by applications in power systems (Shi et al., 2022), EV charging (Lee et al., 2022), and board games (Silver et al., 2017), etc. Controlling such systems can be challenging due to the scale of the system, uncertainty about the model, communication constraints, and the interaction between agents. Inspired by the recent success of reinforcement learning (RL), there is an increasing interest in applying RL methods to environments with multi-agent interactions. However, in multi-agent RL (MARL), the analysis of the system behavior becomes challenging due to the time-varying nature of the environment faced by each agent, which results from the (time-varying) competitive decisions of other agents. As a result, the theoretical analysis of MARL, especially in the competitive setting, is still limited, especially when it comes to large-scale systems. The results of MARL in competitive settings to this point have tended to focus on games with a small number of players, e.g., 2-player zero-sum stochastic games (Littman, 1994), or games with special structure, e.g., Markov potential games (MPGs) (Fox et al., 2022). MPGs in particular provide a setting in which the challenges of large-scale systems can be studied.

This work presents a 3D multi-robot exploration framework for a team of UGVs moving on uneven terrains. The framework was designed by casting the two-level coordination strategy presented in [1] into the context of multi-robot exploration. The resulting distributed exploration technique minimizes and explicitly manages the occurrence of conflicts and interferences in the robot team. Each robot selects where to scan next by using a receding horizon next-best-view approach [2]. A sampling-based tree is directly expanded on segmented traversable regions of the terrain 3D map to generate the candidate next viewpoints. During the exploration, users can assign locations with higher priorities on-demand to steer the robot exploration toward areas of interest. The proposed framework can be also used to perform coverage tasks in the case a map of the environment is a priori provided as input. An open-source implementation is available online.

Recent advances in machine learning models allowed robots to identify objects on a perceptual nonsymbolic level (e.g., through sensor fusion and natural language understanding). However, these primarily black-box learning models still lack interpretation and transferability and require high data and computational demand. An alternative solution is to teach a robot on both perceptual nonsymbolic and conceptual symbolic levels through hybrid neurosymbolic learning approaches with expert feedback (i.e., human-in-the-loop learning). This work proposes a concept for this user-centered hybrid learning paradigm that focuses on robotic surgical situations. While most recent research focused on hybrid learning for non-robotic and some generic robotic domains, little work focuses on surgical robotics. We survey this related research while focusing on human-in-the-loop surgical robotic systems. This evaluation highlights the most prominent solutions for autonomous surgical robots and the challenges surgeons face when interacting with these systems. Finally, we envision possible ways to address these challenges using online apprenticeship learning based on implicit and explicit feedback from expert surgeons.

We propose Grab-UCB, a graph-kernel multi-arms bandit algorithm to learn online the optimal source placement in large scale networks, such that the reward obtained from a priori unknown network processes is maximized. The uncertainty calls for online learning, which suffers however from the curse of dimensionality. To achieve sample efficiency, we describe the network processes with an adaptive graph dictionary model, which typically leads to sparse spectral representations. This enables a data-efficient learning framework, whose learning rate scales with the dimension of the spectral representation model instead of the one of the network. We then propose Grab-UCB, an online sequential decision strategy that learns the parameters of the spectral representation while optimizing the action strategy. We derive the performance guarantees that depend on network parameters, which further influence the learning curve of the sequential decision strategy We introduce a computationally simplified solving method, Grab-arm-Light, an algorithm that walks along the edges of the polytope representing the objective function. Simulations results show that the proposed online learning algorithm outperforms baseline offline methods that typically separate the learning phase from the testing one. The results confirm the theoretical findings, and further highlight the gain of the proposed online learning strategy in terms of cumulative regret, sample efficiency and computational complexity.

Time is a crucial factor in modelling dynamic behaviours of intelligent agents: activities have a determined temporal duration in a real-world environment, and previous actions influence agents' behaviour. In this paper, we propose a language for modelling concurrent interaction between agents that also allows the specification of temporal intervals in which particular actions occur. Such a language exploits a timed version of Abstract Argumentation Frameworks to realise a shared memory used by the agents to communicate and reason on the acceptability of their beliefs with respect to a given time interval. An interleaving model on a single processor is used for basic computation steps, with maximum parallelism for time elapsing. Following this approach, only one of the enabled agents is executed at each moment. To demonstrate the capabilities of language, we also show how it can be used to model interactions such as debates and dialogue games taking place between intelligent agents. Lastly, we present an implementation of the language that can be accessed via a web interface. Under consideration in Theory and Practice of Logic Programming (TPLP).

In this work, we focus on the communication aspect of decentralized learning, which involves multiple agents training a shared machine learning model using decentralized stochastic gradient descent (D-SGD) over distributed data. In particular, we investigate the impact of broadcast transmission and probabilistic random access policy on the convergence performance of D-SGD, considering the broadcast nature of wireless channels and the link dynamics in the communication topology. Our results demonstrate that optimizing the access probability to maximize the expected number of successful links is a highly effective strategy for accelerating the system convergence.

Fast moving unmanned aerial vehicles (UAVs) are well suited for aerial surveillance, but are limited by their battery capacity. To increase their endurance UAVs can be refueled on slow moving unmanned ground vehicles (UGVs). The cooperative routing of UAV-UGV multi-agent system to survey vast regions within their speed and fuel constraints is a computationally challenging problem, but can be simplified with heuristics. Here we present multiple heuristics to enable feasible and sufficiently optimal solutions to the problem. Using the UAV fuel limits and the minimum set cover algorithm, the UGV refueling stops are determined. These refueling stops enable the allocation of mission points to the UAV and UGV. A standard traveling salesman formulation and a vehicle routing formulation with time windows, dropped visits, and capacity constraints is used to solve for the UGV and UAV route, respectively. Experimental validation on a small-scale testbed (http://tiny.cc/8or8vz) underscores the effectiveness of our multi-agent approach.

We envision a warehouse in which dozens of mobile robots and human pickers work together to collect and deliver items within the warehouse. The fundamental problem we tackle, called the order-picking problem, is how these worker agents must coordinate their movement and actions in the warehouse to maximise performance (e.g. order throughput). Established industry methods using heuristic approaches require large engineering efforts to optimise for innately variable warehouse configurations. In contrast, multi-agent reinforcement learning (MARL) can be flexibly applied to diverse warehouse configurations (e.g. size, layout, number/types of workers, item replenishment frequency), as the agents learn through experience how to optimally cooperate with one another. We develop hierarchical MARL algorithms in which a manager assigns goals to worker agents, and the policies of the manager and workers are co-trained toward maximising a global objective (e.g. pick rate). Our hierarchical algorithms achieve significant gains in sample efficiency and overall pick rates over baseline MARL algorithms in diverse warehouse configurations, and substantially outperform two established industry heuristics for order-picking systems.

There are two major challenges for scaling up robot navigation around dynamic obstacles: the complex interaction dynamics of the obstacles can be hard to model analytically, and the complexity of planning and control grows exponentially in the number of obstacles. Data-driven and learning-based methods are thus particularly valuable in this context. However, data-driven methods are sensitive to distribution drift, making it hard to train and generalize learned models across different obstacle densities. We propose a novel method for compositional learning of Sequential Neural Control Barrier models (SNCBFs) to achieve scalability. Our approach exploits an important observation: the spatial interaction patterns of multiple dynamic obstacles can be decomposed and predicted through temporal sequences of states for each obstacle. Through decomposition, we can generalize control policies trained only with a small number of obstacles, to environments where the obstacle density can be 100x higher. We demonstrate the benefits of the proposed methods in improving dynamic collision avoidance in comparison with existing methods including potential fields, end-to-end reinforcement learning, and model-predictive control. We also perform hardware experiments and show the practical effectiveness of the approach in the supplementary video.