arXiv subjects

Haejoon Lee

Publications and source records attributed to Haejoon Lee.

18 recordsLinked to original sources

arXiv2026

Distributed Model-Based Diffusion For Scalable Multi-Robot Trajectory Optimization

Trajectory optimization for multi-robot systems remains a critical challenge, particularly when navigating highly non-convex, non-linear, and non-differentiable environments. While Model-Based Diffusion (MBD) has recently emerged as a promising sampling-based optimization paradigm for single-robot trajectory generation, extending it to multi-robot systems results in a centralized, high-dimensional inference problem that (i) suffers from poor sample efficiency due to the curse of dimensionality and (ii) requires global access to all robots' dynamics, constraints, and objectives. To address this, we propose Distributed Model-Based Diffusion (DMBD), a distributed server-robot framework that decomposes the reverse diffusion process into local conditional reverse diffusion processes. This decomposition enables each robot to iteratively perform denoising independently within its own control subspace while conditioning on the current trajectory estimates of the other robots that are aggregated and broadcast by the server. Extensive simulations in goal swapping, multi-floor coverage, parking, and rush-hour scenarios demonstrate that DMBD achieves strong scalability, solving many challenging coordination tasks in sub-seconds and significantly outperforming existing baselines.

cs.RO↗

arXiv2026

Distributionally Robust Safety Under Arbitrary Uncertainties: A Safety Filtering Approach

We study how to ensure probabilistic safety for nonlinear systems under distributional ambiguity. Our approach builds on a backup-based safety filtering framework that switches between a high-performance nominal policy and a certified backup policy to ensure safety. To handle arbitrary uncertainties from ambiguous distributions, i.e., where the distribution is not of specific structure and the true distribution is unknown, we adopt a distributionally robust (DR) formulation using Wasserstein ambiguity sets. Rather than solving a high-dimensional DR trajectory optimization problem online, we exploit the structure of backup-based safety filtering to reduce safety certification to a one-dimensional search over the switching time between nominal and backup policies. We then develop a sampling-based certification procedure with finite-sample guarantees, where empirical failure probabilities are compared against a Wasserstein-inflated threshold. We validate our method across three systems, from a Dubins vehicle to a high-speed racing car and a fighter jet, demonstrating the broad applicability and computational efficiency.

cs.RO↗

arXiv2026

Robust Multi-Agent LLMs under Byzantine Faults

Large language model (LLM) agents increasingly collaborate over peer-to-peer networks to improve their reliability. However, these same interactions can also introduce vulnerability to unreliable or Byzantine agents that can propagate incorrect information and degrade overall system performance. To address this, we propose Self-Anchored Consensus (SAC), a fully decentralized filter-and-refine protocol in which agents iteratively exchange responses, locally evaluate and filter unreliable messages, and refine their own outputs. We present $(F{+}1)$-robustness conditions on the communication graph that ensure honest agents preserve and propagate reliable information despite Byzantine influence. Experiments across diverse open- and closed-weight LLMs on mathematical and commonsense reasoning benchmarks show that SAC effectively suppresses Byzantine influence and consistently improves performance across diverse communication topologies, whereas prior methods degrade significantly under Byzantine attacks.

cs.MA↗

arXiv2026

Fully Byzantine-Resilient Distributed Multi-Agent Q-Learning

We study Byzantine-resilient distributed multi-agent reinforcement learning (MARL), where agents must collaboratively learn optimal value functions over a compromised communication network. Existing resilient MARL approaches typically guarantee almost sure convergence only to near-optimal value functions, or require restrictive assumptions to ensure convergence to optimal solution. As a result, agents may fail to learn the optimal policies under these methods. To address this, we propose a novel distributed Q-learning algorithm, under which all agents' value functions converge almost surely to the optimal value functions despite Byzantine edge attacks. The key idea is a redundancy-based filtering mechanism that leverages two-hop neighbor information to validate incoming messages, while preserving bidirectional information flow. We then introduce a new topological condition for the convergence of our algorithm, present a systematic method to construct such networks, and prove that this condition can be verified in polynomial time. We validate our results through simulations, showing that our method converges to the optimal solutions, whereas prior methods fail under Byzantine edge attacks.

cs.MA↗

arXiv2025

Partial Resilient Leader-Follower Consensus in Time-Varying Graphs

This work studies resilient leader-follower consensus with a bounded number of adversaries. Existing approaches typically require robustness conditions of the entire network to guarantee resilient consensus. However, the behavior of such systems when these conditions are not fully met remains unexplored. To address this gap, we introduce the notion of partial leader-follower consensus, in which a subset of non-adversarial followers successfully tracks the leader's reference state despite insufficient robustness. We propose a novel distributed algorithm - the Bootstrap Percolation and Mean Subsequence Reduced (BP-MSR) algorithm - and establish sufficient conditions for individual followers to achieve consensus via the BP-MSR algorithm in arbitrary time-varying graphs. We validate our findings through simulations, demonstrating that our method guarantees partial leader-follower consensus, even when standard resilient consensus algorithms fail.

cs.MA↗

arXiv2025

Multi-Robot Allocation for Information Gathering in Non-Uniform Spatiotemporal Environments

Autonomous robots are increasingly deployed to estimate spatiotemporal fields (e.g., wind, temperature, gas concentration) that vary across space and time. We consider environments divided into non-overlapping regions with distinct spatial and temporal dynamics, termed non-uniform spatiotemporal environments. Gaussian Processes (GPs) can be used to estimate these fields. The GP model depends on a kernel that encodes how the field co-varies in space and time, with its spatial and temporal lengthscales defining the correlation. Hence, when these lengthscales are incorrect or do not correspond to the actual field, the estimates of uncertainty can be highly inaccurate. Existing GP methods often assume one global lengthscale or update only periodically; some allow spatial variation but ignore temporal changes. To address these limitations, we propose a two-phase framework for multi-robot field estimation. Phase 1 uses a variogram-driven planner to learn region-specific spatial lengthscales. Phase 2 employs an allocation strategy that reassigns robots based on the current uncertainty, and updates sampling as temporal lengthscales are refined. For encoding uncertainty, we utilize clarity, an information metric from our earlier work. We evaluate the proposed method across diverse environments and provide convergence analysis for spatial lengthscale estimation, along with dynamic regret bounds quantifying the gap to the oracle's allocation sequence.

cs.RO↗

arXiv2025

Combinatorial Control Barrier Functions: Nested Boolean and p-choose-r Compositions of Safety Constraints

This paper investigates the problem of composing multiple control barrier functions (CBFs) -- and matrix control barrier functions (MCBFs) -- through logical and combinatorial operations. Standard CBF formulations naturally enable conjunctive (AND) combinations, but disjunctive (OR) and more general logical structures introduce nonsmoothness and possibly a combinatorial blow-up in the number of logical combinations. We introduce the framework of combinatorial CBFs that addresses p-choose-r safety specifications and their nested composition. The proposed framework ensures safety for the exact safe set in a scalable way, using the original number of primitive constraints. We establish theoretical guarantees on safety under these compositions, and we demonstrate their use on a patrolling problem in a multi-agent system.

eess.SY↗

arXiv2025

Reformulations of Quadratic Programs for Lipschitz Continuity

Optimization-based controllers often lack regularity guarantees, such as Lipschitz continuity, when multiple constraints are present. When used to control a dynamical system, these conditions are essential to ensure the existence and uniqueness of the system's trajectory. Here we propose a general method to convert a Quadratic Program (QP) into a Second-Order Cone Problem (SOCP), which is shown to be Lipschitz continuous. Key features of our approach are that (i) the regularity of the resulting formulation does not depend on the structural properties of the constraints, such as the linear independence of their gradients; and (ii) it admits a closed-form solution, which is not available for general QPs with multiple constraints, enabling faster computation. We support our method with rigorous analysis and examples.

math.OC↗

arXiv2025

Minimal Construction of Graphs with Maximum Robustness

The notions of $r$-robustness and $(r,s)$-robustness of a network have been earlier introduced in the literature to achieve resilient consensus in the presence of misbehaving agents. However, while higher robustness levels enable networks to tolerate a higher number of misbehaving agents, they also require dense communication structures, which are not always desirable for systems with limited communication ranges, energy, and resources. Therefore, this paper studies the fundamental structures behind $r$-robustness and $(r,s)$- robustness properties in two ways. (a) We first establish tight necessary conditions on the number of edges that an undirected graph with an arbitrary number of nodes must have to achieve maximum $r$- and $(r,s)$-robustness. (b) We then use these conditions to construct two classes of undirected graphs, referred to as $\gamma$- and $(\gamma,\gamma)$-Minimal Edge Robust Graphs (MERGs), that provably achieve maximum robustness with minimal numbers of edges. We demonstrate the effectiveness of our method via comparison against existing robust graph structures and a set of simulations.

eess.SY↗

arXiv2025

PhotonSplat: 3D Scene Reconstruction and Colorization from SPAD Sensors

Advances in 3D reconstruction using neural rendering have enabled high-quality 3D capture. However, they often fail when the input imagery is corrupted by motion blur, due to fast motion of the camera or the objects in the scene. This work advances neural rendering techniques in such scenarios by using single-photon avalanche diode (SPAD) arrays, an emerging sensing technology capable of sensing images at extremely high speeds. However, the use of SPADs presents its own set of unique challenges in the form of binary images, that are driven by stochastic photon arrivals. To address this, we introduce PhotonSplat, a framework designed to reconstruct 3D scenes directly from SPAD binary images, effectively navigating the noise vs. blur trade-off. Our approach incorporates a novel 3D spatial filtering technique to reduce noise in the renderings. The framework also supports both no-reference using generative priors and reference-based colorization from a single blurry image, enabling downstream applications such as segmentation, object detection and appearance editing tasks. Additionally, we extend our method to incorporate dynamic scene representations, making it suitable for scenes with moving objects. We further contribute PhotonScenes, a real-world multi-view dataset captured with the SPAD sensors.

eess.IV↗

arXiv2025

Feasibility Analysis and Constraint Selection in Optimization-Based Controllers

Control synthesis under constraints is at the forefront of research on autonomous systems, in part due to its broad application from low-level control to high-level planning, where computing control inputs is typically cast as a constrained optimization problem. Assessing feasibility of the constraints and selecting among subsets of feasible constraints is a challenging yet crucial problem. In this work, we provide a novel theoretical analysis that yields necessary and sufficient conditions for feasibility assessment of linear constraints and based on this analysis, we develop novel methods for feasible constraint selection in the context of control of autonomous systems. Through a series of simulations, we demonstrate that our algorithms achieve performance comparable to state-of-the-art methods while offering improved computational efficiency. Importantly, our analysis provides a novel theoretical framework for assessing, analyzing and handling constraint infeasibility.

math.OC↗

arXiv2025

Enabling Safety for Aerial Robots: Planning and Control Architectures

Ensuring safe autonomy is crucial for deploying aerial robots in real-world applications. However, safety is a multifaceted challenge that must be addressed from multiple perspectives, including navigation in dynamic environments, operation under resource constraints, and robustness against adversarial attacks and uncertainties. In this paper, we present the authors' recent work that tackles some of these challenges and highlights key aspects that must be considered to enhance the safety and performance of autonomous aerial systems. All presented approaches are validated through hardware experiments.

cs.RO↗

arXiv2025

Distributed Resilience-Aware Control in Multi-Robot Networks

Ensuring resilient consensus in multi-robot systems with misbehaving agents remains a challenge, as many existing network resilience properties are inherently combinatorial and globally defined. While previous works have proposed control laws to enhance or preserve resilience in multi-robot networks, they often assume a fixed topology with known resilience properties, or require global state knowledge. These assumptions may be impractical in physically-constrained environments, where safety and resilience requirements are conflicting, or when misbehaving agents share inaccurate state information. In this work, we propose a distributed control law that enables each robot to guarantee resilient consensus and safety during its navigation without fixed topologies using only locally available information. To this end, we establish a sufficient condition for resilient consensus in time-varying networks based on the degree of non-misbehaving or normal agents. Using this condition, we design a Control Barrier Function (CBF)-based controller that guarantees resilient consensus and collision avoidance without requiring estimates of global state and/or control actions of all other robots. Finally, we validate our method through simulations.

eess.SY↗

arXiv2024

Construction of the Sparsest Maximally r-Robust Graphs

In recent years, the notion of r-robustness for the communication graph of the network has been introduced to address the challenge of achieving consensus in the presence of misbehaving agents. Higher r-robustness typically implies higher tolerance to malicious information towards achieving resilient consensus, but it also implies more edges for the communication graph. This in turn conflicts with the need to minimize communication due to limited resources in real-world applications (e.g., multi-robot networks). In this paper, our contributions are twofold. (a) We provide the necessary subgraph structures and tight lower bounds on the number of edges required for graphs with a given number of nodes to achieve maximum robustness. (b) We then use the results of (a) to introduce two classes of graphs that maintain maximum robustness with the least number of edges. Our work is validated through a series of simulations.

eess.SY↗

arXiv2024

Maintaining Strong r-Robustness in Reconfigurable Multi-Robot Networks using Control Barrier Functions

In leader-follower consensus, strong r-robustness of the communication graph provides a sufficient condition for followers to achieve consensus in the presence of misbehaving agents. Previous studies have assumed that robots can form and/or switch between predetermined network topologies with known robustness properties. However, robots with distance-based communication models may not be able to achieve these topologies while moving through spatially constrained environments, such as narrow corridors, to complete their objectives. This paper introduces a Control Barrier Function (CBF) that ensures robots maintain strong r-robustness of their communication graph above a certain threshold without maintaining any fixed topologies. Our CBF directly addresses robustness, allowing robots to have flexible reconfigurable network structure while navigating to achieve their objectives. The efficacy of our method is tested through various simulation and hardware experiments.

cs.RO↗

arXiv2024

Computational Imaging for Long-Term Prediction of Solar Irradiance

The occlusion of the sun by clouds is one of the primary sources of uncertainties in solar power generation, and is a factor that affects the wide-spread use of solar power as a primary energy source. Real-time forecasting of cloud movement and, as a result, solar irradiance is necessary to schedule and allocate energy across grid-connected photovoltaic systems. Previous works monitored cloud movement using wide-angle field of view imagery of the sky. However, such images have poor resolution for clouds that appear near the horizon, which reduces their effectiveness for long term prediction of solar occlusion. Specifically, to be able to predict occlusion of the sun over long time periods, clouds that are near the horizon need to be detected, and their velocities estimated precisely. To enable such a system, we design and deploy a catadioptric system that delivers wide-angle imagery with uniform spatial resolution of the sky over its field of view. To enable prediction over a longer time horizon, we design an algorithm that uses carefully selected spatio-temporal slices of the imagery using estimated wind direction and velocity as inputs. Using ray-tracing simulations as well as a real testbed deployed outdoors, we show that the system is capable of predicting solar occlusion as well as irradiance for tens of minutes in the future, which is an order of magnitude improvement over prior work.

cs.CV↗

arXiv2023

Toward Automated Detection of Microbleeds with Anatomical Scale Localization: A Complete Clinical Diagnosis Support Using Deep Learning

Cerebral Microbleeds (CMBs) are chronic deposits of small blood products in the brain tissues, which have explicit relation to various cerebrovascular diseases depending on their anatomical location, including cognitive decline, intracerebral hemorrhage, and cerebral infarction. However, manual detection of CMBs is a time-consuming and error-prone process because of their sparse and tiny structural properties. The detection of CMBs is commonly affected by the presence of many CMB mimics that cause a high false-positive rate (FPR), such as calcification and pial vessels. This paper proposes a novel 3D deep learning framework that does not only detect CMBs but also inform their anatomical location in the brain (i.e., lobar, deep, and infratentorial regions). For the CMB detection task, we propose a single end-to-end model by leveraging the U-Net as a backbone with Region Proposal Network (RPN). To significantly reduce the FPs within the same single model, we develop a new scheme, containing Feature Fusion Module (FFM) that detects small candidates utilizing contextual information and Hard Sample Prototype Learning (HSPL) that mines CMB mimics and generates additional loss term called concentration loss using Convolutional Prototype Learning (CPL). The anatomical localization task does not only tell to which region the CMBs belong but also eliminate some FPs from the detection task by utilizing anatomical information. The results show that the proposed RPN that utilizes the FFM and HSPL outperforms the vanilla RPN and achieves a sensitivity of 94.66% vs. 93.33% and an average number of false positives per subject (FPavg) of 0.86 vs. 14.73. Also, the anatomical localization task further improves the detection performance by reducing the FPavg to 0.56 while maintaining the sensitivity of 94.66%.

eess.IV↗

arXiv2022

Optimal Control of Several Motion Models

This paper is devoted to the study of the dynamic optimization of several controlled crowd motion models in the general planar settings, which is an application of a class of optimal control problems involving a general nonconvex sweeping process with perturbations. A set of necessary optimality conditions for such optimal control problems involving the crowd motion models with multiple agents and obstacles is obtained and analyzed. Several effective algorithms based on such necessary optimality conditions are proposed and various nontrivial illustrative examples together with their simulations are also presented. The implementation of all the considered motion models can be found via the link: https://github.com/tancao1128/Optimal_Control_of_Several_Motion_Models with the instruction and demonstration video uploaded at https://www.youtube.com/watch?v=B8DQ0wvCtIQ.

math.OC↗