Language models (LMs) possess a strong capability to comprehend natural language, making them effective in translating human instructions into detailed plans for simple robot tasks. Nevertheless, it remains a significant challenge to handle long-horizon tasks, especially in subtask identification and allocation for cooperative heterogeneous robot teams. To address this issue, we propose a Language Model-Driven Multi-Agent PDDL Planner (LaMMA-P), a novel multi-agent task planning framework that achieves state-of-the-art performance on long-horizon tasks. LaMMA-P integrates the strengths of the LMs' reasoning capability and the traditional heuristic search planner to achieve a high success rate and efficiency while demonstrating strong generalization across tasks. Additionally, we create MAT-THOR, a comprehensive benchmark that features household tasks with two different levels of complexity based on the AI2-THOR environment. The experimental results demonstrate that LaMMA-P achieves a 105% higher success rate and 36% higher efficiency than existing LM-based multi-agent planners. The experimental videos, code, and datasets of this work as well as the detailed prompts used in each module are available at https://lamma-p.github.io.

Effective environment perception is crucial for enabling downstream robotic applications. Individual robotic agents often face occlusion and limited visibility issues, whereas multi-agent systems can offer a more comprehensive mapping of the environment, quicker coverage, and increased fault tolerance. In this paper, we propose a collaborative multi-agent perception system where agents collectively learn a neural radiance field (NeRF) from posed RGB images to represent a scene. Each agent processes its local sensory data and shares only its learned NeRF model with other agents, reducing communication overhead. Given NeRF's low memory footprint, this approach is well-suited for robotic systems with limited bandwidth, where transmitting all raw data is impractical. Our distributed learning framework ensures consistency across agents' local NeRF models, enabling convergence to a unified scene representation. We show the effectiveness of our method through an extensive set of experiments on datasets containing challenging real-world scenes, achieving performance comparable to centralized mapping of the environment where data is sent to a central server for processing. Additionally, we find that multi-agent learning provides regularization benefits, improving geometric consistency in scenarios with sparse input views. We show that in such scenarios, multi-agent mapping can even outperform centralized training.

Many decision-making problems feature multiple objectives where it is not always possible to know the preferences of a human or agent decision-maker for different objectives. However, demonstrated behaviors from the decision-maker are often available. This research proposes a dynamic weight-based preference inference (DWPI) algorithm that can infer the preferences of agents acting in multi-objective decision-making problems from demonstrations. The proposed algorithm is evaluated on three multi-objective Markov decision processes: Deep Sea Treasure, Traffic, and Item Gathering, and is compared to two existing preference inference algorithms. Empirical results demonstrate significant improvements compared to the baseline algorithms, in terms of both time efficiency and inference accuracy. The DWPI algorithm maintains its performance when inferring preferences for sub-optimal demonstrations. Moreover, the DWPI algorithm does not necessitate any interactions with the user during inference - only demonstrations are required. We provide a correctness proof and complexity analysis of the algorithm and statistically evaluate the performance under different representation of demonstrations.

A key component of dyadic spoken interactions is the contextually relevant non-verbal gestures, such as head movements that reflect a listener's response to the interlocutor's speech. Although significant progress has been made in the context of generating co-speech gestures, generating listener's response has remained a challenge. We introduce the task of generating continuous head motion response of a listener in response to the speaker's speech in real time. To this end, we propose a graph-based end-to-end crossmodal model that takes interlocutor's speech audio as input and directly generates head pose angles (roll, pitch, yaw) of the listener in real time. Different from previous work, our approach is completely data-driven, does not require manual annotations or oversimplify head motion to merely nods and shakes. Extensive evaluation on the dyadic interaction sessions on the IEMOCAP dataset shows that our model produces a low overall error (4.5 degrees) and a high frame rate, thereby indicating its deployability in real-world human-robot interaction systems. Our code is available at - https://github.com/bigzen/Active-Listener

The continued transition towards electric mobility will decrease energy tax revenues worldwide, which has substantial implications for government funds. At the same time, demand for transportation is ever increasing, which in turn increases congestion problems. Combining both challenges, this paper assesses the effectiveness of congestion pricing as a sustainable revenue stream to offset fuel tax loss in 2030 while simultaneously enhancing efficiency in the transport sector. A congestion-based toll that is road-and-time-variant is simulated for the greater Berlin area in Germany using the multi-agent transport simulation (MATSim) software. Through the simulation results, this paper quantifies the impacts of the toll on the governmental revenue, traffic management, environment, social welfare, and the distribution effects. We find that the revenue from congestion tolls in a metropolitan area can compensate the reduction in passenger car fuel tax. Furthermore, a remarkable welfare surplus is observed. The toll also successfully incentivises transport users to adjust their travel behaviour, which reduces traffic delay time by 28%. CO2 emissions as a key metric for decarbonisation of the transport sector decrease by more than 5%. The analysis of the distribution effects suggests that a redistribution plan with a focus on the middle-low-income residents and the outer boroughs could help the policy gain more public acceptance.

We consider the problem of classification with a (peer-to-peer) network of heterogeneous and partially informative agents, each receiving local data generated by an underlying true class, and equipped with a classifier that can only distinguish between a subset of the entire set of classes. We propose an iterative algorithm that uses the posterior probabilities of the local classifier and recursively updates each agent's local belief on all the possible classes, based on its local signals and belief information from its neighbors. We then adopt a novel distributed min-rule to update each agent's global belief and enable learning of the true class for all agents. We show that under certain assumptions, the beliefs on the true class converge to one asymptotically almost surely. We provide the asymptotic convergence rate, and demonstrate the performance of our algorithm through simulation with image data and experimented with random forest classifiers and MobileNet.

Communication between humans and robots (or virtual agents) is essential for interaction and often inspired by human communication, which uses gestures, facial expressions, gaze direction, and other explicit and implicit means. This work presents an interaction experiment where humans and virtual agents interact through explicit (gestures, manual entries using mouse and keyboard, voice, sound, and information on screen) and implicit (gaze direction, location, facial expressions, and raise of eyebrows) communication to evaluate the effect of mixed explicit-implicit communication against purely explicit communication. Results obtained using Bayesian parameter estimation show that the number of errors and task execution time did not significantly change when mixed explicit and implicit communications were used, and neither the perceived efficiency of the interaction. In contrast, acceptance, sociability, and transparency of the virtual agent increased when using mixed communication modalities (88.3%, 92%, and 92.9% of the effect size posterior distribution of each variable, respectively, were above the upper limit of the region of practical equivalence). This suggests that task-related measures, such as time, number of errors, and perceived efficiency of the interaction, have not been influenced by the communication type in our particular experiment. However, the improvement of subjective measures related to the virtual agent, such as acceptance, sociability, and transparency, suggests that humans are more receptive to mixed explicit and implicit communications.

The best policy achieves an average seeker success rate of 84.2% in simulation and 80% in real-world experiments in a challenging 3 seekers vs 3 hiders setting with random map layouts. In comparison, the baseline policy has only 36.4% in simulation and 55% in real-world. Interesting collaborative behaviors among seekers are observed during deployment, such as strategically navigating to anticipate and intercept hiders or effectively blocking key paths as a team. Abstract -- Learning collaborative behaviors is essential for multi-agent systems. Traditionally, multi-agent reinforcement learning solves this implicitly through a joint reward and centralized observations, assuming collaborative behavior will emerge. Other studies propose to learn from demonstrations of a group of collaborative experts. Instead, we propose an efficient and explicit way of learning collaborative behaviors in multi-agent systems by leveraging expertise from only a single human. Our insight is that humans can naturally take on various roles in a team. We show that agents can effectively learn to collaborate by allowing a human operator to dynamically switch between controlling agents for a short period and incorporating a human-like theory-of-mind model of teammates. Our experiments showed that our method improves the success rate of a challenging collaborative hide-and-seek task by up to 58 % with only 40 minutes of single-human guidance.

Unlabeled motion planning involves assigning a set of robots to target locations while ensuring collision avoidance, aiming to minimize the total distance traveled. The problem forms an essential building block for multi-robot systems in applications such as exploration, surveillance, and transportation. We address this problem in a decentralized setting where each robot knows only the positions of its $k$-nearest robots and $k$-nearest targets. This scenario combines elements of combinatorial assignment and continuous-space motion planning, posing significant scalability challenges for traditional centralized approaches. To overcome these challenges, we propose a decentralized policy learned via a Graph Neural Network (GNN). The GNN enables robots to determine (1) what information to communicate to neighbors and (2) how to integrate received information with local observations for decision-making. We train the GNN using imitation learning with the centralized Hungarian algorithm as the expert policy, and further fine-tune it using reinforcement learning to avoid collisions and enhance performance. Extensive empirical evaluations demonstrate the scalability and effectiveness of our approach. The GNN policy trained on 100 robots generalizes to scenarios with up to 500 robots, outperforming state-of-the-art solutions by 8.6\% on average and significantly surpassing greedy decentralized methods. This work lays the foundation for solving multi-robot coordination problems in settings where scalability is important.

In this paper, we propose a novel and generalizable zero-shot knowledge transfer framework that distills expert sports navigation strategies from web videos into robotic systems with adversarial constraints and out-of-distribution image trajectories. Our pipeline enables diffusion-based imitation learning by reconstructing the full 3D task space from multiple partial views, warping it into 2D image space, closing the planning loop within this 2D space, and transfer constrained motion of interest back to task space. Additionally, we demonstrate that the learned policy can serve as a local planner in conjunction with position control. We apply this framework in the wheelchair tennis navigation problem to guide the wheelchair into the ball-hitting region. Our pipeline achieves a navigation success rate of 97.67% in reaching real-world recorded tennis ball trajectories with a physical robot wheelchair, and achieve a success rate of 68.49% in a real-world, real-time experiment on a full-sized tennis court.