Affiliation: Università della Calabria, Assistant Professor
Poster Title: Distributed Receding Horizon Control for Safe Multi-Agent Autonomous Transportation Under LiDAR-Driven Graph Updates (Other Contributors: Francesco Tedesco, Giuseppe Franzè)
Poster Abstract: This poster presents a receding horizon control framework for multi-robot navigation in dynamic environments, with particular focus on autonomous transportation and logistics scenarios where multiple vehicles must safely coordinate in the presence of moving obstacles and time-varying path availability. The proposed approach combines graph-based motion planning with distributed robust set-theoretic model predictive control, enabling each robot to compute collision-free motions while accounting for local constraints, mutual interactions, and online updates of the navigation graph. In particular, LiDAR-driven graph updates are exploited to adapt the navigation structure in real time when the environment changes due to the presence of dynamic agents or unexpected obstructions. The resulting framework is designed to improve safety, computational tractability, and flexibility in structured yet evolving environments, such as industrial transportation systems and warehouse-like settings. The poster will discuss the main control architecture, the role of online graph adaptation, and the potential of the method for scalable coordination of autonomous vehicles operating in shared spaces.
Affiliation: Cornell University, Master's Student
Poster Title: A Coordinated Routing Approach for Enhancing Bus Timeliness and Travel Efficiency in Mixed-Traffic Environment
Poster Abstract: This work proposes a coordinated routing approach that investigates the use of connected and automated vehicles (CAVs) in dedicated bus lanes. The aim is to improve bus schedule adherence while enhancing the travel efficiency of CAVs during the transitional phase of mixed traffic environments. Our approach utilizes real-time traffic data to dynamically reroute CAVs in anticipation of congestion. By continuously monitoring traffic conditions on dedicated lanes and tracking the real-time positions of buses, the system adjusts CAV routes in advance to avoid potential interference with operating buses. This cooperation reduces CAV travel times and minimizes delays that impact transit services. The proposed strategy is validated using microscopic traffic simulations in SUMO. The results demonstrate significant improvements in both transit on-time performance and CAV travel efficiency across a range of traffic conditions.
Affiliation: Dartmouth College, PhD Student
Poster Title: Misspecification in Model Predictive Game Controllers: Stability and Sensitivity with Heterogeneous Objective Conjectures (Other Contributors: Bryce L. Ferguson)
Poster Abstract: Multi-agent decision-making involves agents making strategic decisions while considering or predicting each other’s behavior. Model predictive games are a class of controllers in which an agent iteratively solves a finite-horizon game to predict the collective behavior of a multi-agent system and synthesize their own control action from the first time step in a receding-horizon fashion. When multiple agents implement these types of controllers, there may exist misspecifications in their respective game models resulting from not accurately knowing other agents’ objectives. This work studies the effects of these prediction misalignments by providing criteria for the stability of systems of agents deploying model predictive game controllers with heterogeneous game models, as well as the sensitivity of the resulting equilibria to individual agents’ game parameters.
Affiliation: George Washington University, PhD student
Poster Title: Robust Multi-Agent Reinforcement Learning for Small UAS Separation Assurance under GPS Degradation and Spoofing (Other Contributors: Fillippos Fotiadis, Ufuk Topcu and Peng Wei)
Poster Abstract: We address robust separation assurance for small Unmanned Aircraft Systems (sUAS) under GPS degradation and spoofing via Multi-Agent Reinforcement Learning (MARL). In cooperative surveillance, each aircraft (or agent) broadcasts its GPS-derived position; when such position broadcasts are corrupted, the entire observed air traffic state becomes unreliable. We cast this state observation corruption as a zero-sum game between the agents and an adversary: with probability R, the adversary perturbs the observed state to maximally degrade each agent's safety performance. We derive a closed-form expression for this adversarial perturbation, bypassing adversarial training entirely and enabling linear-time evaluation in the state dimension. We show that this expression approximates the true worst-case adversarial perturbation with second-order accuracy. We further bound the safety performance gap between clean and corrupted observations, showing that it degrades at most linearly with the corruption probability under Kullback-Leibler regularization. Finally, we integrate the closed-form adversarial policy into a MARL policy gradient algorithm to obtain a robust counter-policy for the agents. In a high-density sUAS simulation, we observe near-zero collision rates under corruption levels up to 35%, outperforming a baseline policy trained without adversarial perturbations.
Affiliation: Worcester Polytechnic Institute, Graduate Research Assistant
Poster Title: Trajectory Optimization for Cooperative Navigation by solving the HJB Equation using PINNs (Other contributors: Michael Steffens, Raghvendra V Cowlagi)
Poster Abstract: Cooperative navigation is a methodology where multiple mobile vehicles share navigational aiding information with the aim of improving the precision and accuracy of localization. This methodology can enable teams of autonomous mobile vehicles to navigate in, say, undersea and subterranean environments where conventional localization methods based on global satellite navigation systems and/or vision do not suffice. In such environments, information can be shared when vehicles are in close proximity. To this end, one approach is to assign the role of an cooperative navigation aids (CNA) to specific vehicles in the team, and to then optimize the trajectories of the remaining vehicles to achieve sufficient proximity to the CNA while conducting their tasks. We formulate this problem as an optimal control problem, where proximity to a moving CNA constitutes a “benefit” to be maximized while traversing between two prespecified fixed locations in the environment. We formulate the associated Hamilton-Jacobi-Bellman (HJB) equation, which encodes necessary and sufficient conditions for a feedback optimal control policy. Such HJB equations are known to be difficult to solve numerically. However, recent advances in physics-informed neural networks (PINNs) have shown promise in efficiently solving ordinary- and partial differential equations. We develop a PINN to solve the HJB equation for the cooperative navigation problem of optimizing a weighted composite objective of maximizing the aid received from a CNA while also minimizing the time of travel. We describe the details of the PINN architecture and demonstrate its effectiveness via numerical simulations.
Affiliation: Texas A&M University
Poster Title: Capability-Aware Heterogeneous Control Barrier Functions for Decentralized Multi-Robot Safe Navigation (Other contributors: Yanze Zhang, Wenhao Luo, Yiwei Lyu)
Poster Abstract: Safe navigation for multi-robot systems requires enforcing safety without sacrificing task efficiency under decentralized decision-making. Existing decentralized methods often assume robot homogeneity, causing shared safety requirements to be non-uniformly interpreted across heterogeneous agents with structurally different dynamics, leading to avoidance constraints infeasible for some robots to satisfy, and thus safety violations or deadlock. We propose Capability-Aware Heterogeneous Control Barrier Function (CA-HCBF), a decentralized framework for consistent safety enforcement and capability-aware coordination in heterogeneous robot teams. We derive a canonical second-order control-affine representation that unifies holonomic and nonholonomic robots under acceleration-level control via canonical transformation and backstepping, avoiding relative-degree mismatch across heterogeneous dynamics. A support-function-based directional capability metric further derives a pairwise responsibility allocation proportional to each robot's motion capability, with a feasibility-aware clipping mechanism constraining each agent's assigned burden to its physically achievable range. Simulations with up to 30 heterogeneous robots and a physical multi-robot demonstration show improved safety and task efficiency over baselines, validating real-world applicability across robots with distinct kinematic constraints.
Affiliation: UC Berkeley, PhD Student
Poster Title: Feature-Based Perception-Aware Multi-UAV Trajectory Planning (Other Contributors: Christian Brommer, Mark Mueller)
Poster Abstract: Multi-agent UAV systems are well-suited for largescale data collection and transportation, though navigation in unstructured, GPS-denied environments remains challenging. Vision-based navigation enables operation without external infrastructure, but the uncertainty in state estimation limits its reliability in multi-agent settings. We propose a trajectory planning framework that incorporates estimator uncertainty by exploiting visual feature observations between agents. The framework maintains a coherent shared map through multiagent frame alignment to prevent independent vision drift, and employs a perception-aware reward that favors trajectories with stronger feature visibility and cross-agent redundancy. Flight data from a controlled two-UAV experiment demonstrate that our alignment module can effectively reduce relative distance error, validating its role in maintaining inter-agent consistency. Simulations show that perception-aware rewards improve feature visibility and coordination while maintaining goal-reaching performance.
Affiliation: Indian Institute of Technology Bombay, Phd Research Scholar
Poster Title: Trajectory Encryption Cooperative Salvo Guidance (Other Contributors: Dr. Abhinav Sinha, Dr. Shashi Ranjan Kumar)
Poster Abstract: This paper introduces the concept of trajectory encryption in cooperative simultaneous target interception, wherein heterogeneity in guidance principles across a team of unmanned autonomous systems is leveraged as a strategic design feature. By employing a mix of heterogeneous time-to-go formulations leading to a cooperative guidance strategy, the swarm of vehicles is able to generate diverse trajectory families. This diversity expands the feasible solution space for simultaneous target interception, enhances robustness under disturbances, and enables flexible time-to-go adjustments without predictable detouring. From an adversarial perspective, heterogeneity obscures the collective interception intent by preventing straightforward prediction of swarm dynamics, effectively acting as an encryption layer in the trajectory domain. Simulations demonstrate that the swarm of heterogeneous vehicles is able to intercept a moving target simultaneously from a diverse set of initial engagement configurations.