Shinkyu Park

We propose a novel framework for decision-making in cooperative grasping for two-robot object transport in constrained environments. The core of the framework is a Conditional Embedding (CE) model consisting of two neural networks that map grasp configuration information into an embedding space. The resulting embedding vectors are then used to identify feasible grasp configurations that allow two robots to collaboratively transport an object. To ensure generalizability across diverse environments and object geometries, the neural networks are trained on a dataset comprising a range of environment maps and object shapes. We employ a supervised learning approach with negative sampling to ensure that the learned embeddings effectively distinguish between feasible and infeasible grasp configurations. Evaluation results across a wide range of environments and objects in simulations demonstrate the model’s ability to reliably identify feasible grasp configurations. We further validate the framework through experiments on a physical robotic platform, confirming its practical applicability.

Inertial localization is particularly valuable in GPS-denied environments such as indoors. However, localization using only Inertial Measurement Units (IMUs) suffers from drift caused by motion-process noise and sensor biases. This paper introduces Uncertainty-aware Map-constrained Inertial Localization (UMLoc), an end-to-end framework that jointly models IMU uncertainty and map constraints to achieve drift-resilient positioning. UMLoc integrates two coupled modules: (1) a Long Short-Term Memory (LSTM) quantile regressor, which estimates the specific quantiles needed to define 68%, 90%, and 95% prediction intervals serving as a measure of localization uncertainty and (2) a Conditioned Generative Adversarial Network (CGAN) with cross-attention that fuses IMU dynamic data with distance-based floor-plan maps to generate geometrically feasible trajectories. The modules are trained jointly, allowing uncertainty estimates to propagate through the CGAN during trajectory generation. UMLoc was evaluated on three datasets, including a newly collected 2-hour indoor benchmark with time-aligned IMU data, ground-truth poses and floor-plan maps. Results show that the method achieves a mean drift ratio of 5.9% over a 70 m travel distance and an average Absolute Trajectory Error (ATE) of 1.36 m, while maintaining calibrated prediction bounds.

This work deals with the problem of stabilizing a multi-agent rigid formation on a general class of planar curves. Namely, we seek to stabilize an equilateral polygonal formation on closed planar differentiable curves after a path sweep. The task of finding an inscribed regular polygon centered at the point of interest is solved via a randomized multi-start Newton-Like algorithm for which one is able to ascertain the existence of a minimizer. Then we design a continuous feedback law that guarantees convergence to, and sufficient sweeping of the curve, followed by convergence to the desired formation vertices while ensuring inter-agent avoidance. The proposed approach is validated through numerical simulations for different classes of curves and different rigid formations. Code: https://github.com/mebbaid/paper-elobaid-ifacwc-2026

Multi-robot Coverage Path Planning (MCPP) addresses the problem of computing paths for multiple robots to effectively cover a large area of interest. Conventional approaches to MCPP typically assume that robots move at fixed velocities, which is often unrealistic in real-world applications where robots must adapt their speeds based on the specific coverage tasks assigned to them.Consequently, conventional approaches often lead to imbalanced workload distribution among robots and increased completion time for coverage tasks. To address this, we introduce a novel Multi-robot Dynamic Coverage Path Planning (MDCPP) algorithm for complete coverage in two-dimensional environments. MDCPP dynamically estimates each robot's remaining workload by approximating the target distribution with Gaussian mixture models, and assigns coverage regions using a capacity-constrained Voronoi diagram. We further develop a distributed implementation of MDCPP for range-constrained robotic networks. Simulation results validate the efficacy of MDCPP, showing qualitative improvements and superior performance compared to an existing sweeping algorithm, and a quantifiable impact of communication range on coverage efficiency.

We propose a decentralized, learning-based framework for dynamic coalition formation in Multi-Robot Task Allocation (MRTA). Our approach extends MAPPO by integrating spatial action maps, robot motion planning, intention sharing, and task allocation revision to enable effective and adaptive coalition formation. Extensive simulation studies confirm the effectiveness of our model, enabling each robot to rely solely on local information to learn timely revisions of task selections and form coalitions with other robots to complete collaborative tasks. The results also highlight the proposed framework's ability to handle large robot populations and adapt to scenarios with diverse task sets.

Distributed multi-target tracking is a canonical task for multi-robot systems, encompassing applications from environmental monitoring to disaster response to surveillance. In many situations the unknown distribution of the targets in a search area is non-uniform, e.g., herds of animals moving together. This paper develops a novel distributed multi-robot multi-target tracking algorithm to effectively search for and track clustered targets. There are two key features. First, there are two parallel estimators, one to provide the best guess of the current states of targets and a second to provide a coarse, long-term distribution of clusters. Second, robots use the power diagram to divide the search space between agents in a way that effectively trades off between tracking detected targets within high density areas and searching for other potential targets. Extensive simulation experiments demonstrate the efficacy of the proposed method and show that it outperforms other approaches in tracking accuracy of clustered targets while maintain good performance for uniformly distributed targets.

We study a multi-agent decision problem in large population games. Agents from multiple populations select strategies for repeated interactions with one another. At each stage of these interactions, agents use their decision-making model to revise their strategy selections based on payoffs determined by an underlying game. Their goal is to learn the strategies that correspond to the Nash equilibrium of the game. However, when games are subject to time delays, conventional decision-making models from the population game literature may result in oscillations in the strategy revision process or convergence to an equilibrium other than the Nash. To address this problem, we propose the Kullback-Leibler Divergence Regularized Learning (KLD-RL) model, along with an algorithm that iteratively updates the model's regularization parameter across a network of communicating agents. Using passivity-based convergence analysis techniques, we show that the KLD-RL model achieves convergence to the Nash equilibrium without oscillations, even for a class of population games that are subject to time delays. We demonstrate our main results numerically on a two-population congestion game and a two-population zero-sum game.

This article proposes an approach to mitigate epidemic spread in a population of strategic agents by encouraging safer behaviors through carefully designed rewards. These rewards, which adapt to the evolving state of the epidemic, are ascribed by a dynamic payoff mechanism we seek to design. We use a modified suspectable-infectious–recovered–susceptible model to track how the epidemic progresses in response to the agents' strategic choices. By employing perturbed best response evolutionary dynamics to model the population's strategic behavior, we extend previous related work so as to allow for noise in the agents' perceptions of the rewards and intrinsic costs of the available strategies. Central to our approach is the use of system-theoretic methods and passivity concepts to obtain a Lyapunov function, ensuring the global asymptotic stability of an endemic equilibrium with minimized infection prevalence under budget constraints. We leverage the Lyapunov function to analyze how the epidemic's spread rate is influenced by the time scale of the payoff mechanism's dynamics. In addition, we derive anytime upper bounds on both the infectious fraction of the population and the instantaneous cost a social planner must incur to control the spread, allowing us to quantify the tradeoff between peak infection prevalence and the corresponding cost. For a class of one-parameter perturbed best response models, we propose a method to learn the model's parameter from data.