arXiv subjects

Vijay Kumar

Publications and source records attributed to Vijay Kumar.

At least 55 records · Page 3Linked to original sources

arXiv2025

TACO: Trajectory-Aware Controller Optimization for Quadrotors

Controller performance in quadrotor trajectory tracking depends heavily on parameter tuning, yet standard approaches often rely on fixed, manually tuned parameters that sacrifice task-specific performance. We present Trajectory-Aware Controller Optimization (TACO), a framework that adapts controller parameters online based on the upcoming reference trajectory and current quadrotor state. TACO employs a learned predictive model and a lightweight optimization scheme to optimize controller gains in real time with respect to a broad class of trajectories, and can also be used to adapt trajectories to improve dynamic feasibility while respecting smoothness constraints. To enable large-scale training, we also introduce a parallelized quadrotor simulator supporting fast data collection on diverse trajectories. Experiments on a variety of trajectory types show that TACO outperforms conventional, static parameter tuning while operating orders of magnitude faster than black-box optimization baselines, enabling practical real-time deployment on a physical quadrotor. Furthermore, we show that adapting trajectories using TACO significantly reduces the tracking error obtained by the quadrotor.

cs.RO↗

arXiv2025

LPAC: Learnable Perception-Action-Communication Loops with Applications to Coverage Control

Coverage control is the problem of navigating a robot swarm to collaboratively monitor features or a phenomenon of interest not known a priori. The problem is challenging in decentralized settings with robots that have limited communication and sensing capabilities. We propose a learnable Perception-Action-Communication (LPAC) architecture for the problem, wherein a convolutional neural network (CNN) processes localized perception; a graph neural network (GNN) facilitates robot communications; finally, a shallow multi-layer perceptron (MLP) computes robot actions. The GNN enables collaboration in the robot swarm by computing what information to communicate with nearby robots and how to incorporate received information. Evaluations show that the LPAC models -- trained using imitation learning -- outperform standard decentralized and centralized coverage control algorithms. The learned policy generalizes to environments different from the training dataset, transfers to larger environments with more robots, and is robust to noisy position estimates. The results indicate the suitability of LPAC architectures for decentralized navigation in robot swarms to achieve collaborative behavior.

cs.RO↗

arXiv2025

PIP-LLM: Integrating PDDL-Integer Programming with LLMs for Coordinating Multi-Robot Teams Using Natural Language

Enabling robot teams to execute natural language commands requires translating high-level instructions into feasible, efficient multi-robot plans. While Large Language Models (LLMs) combined with Planning Domain Description Language (PDDL) offer promise for single-robot scenarios, existing approaches struggle with multi-robot coordination due to brittle task decomposition, poor scalability, and low coordination efficiency. We introduce PIP-LLM, a language-based coordination framework that consists of PDDL-based team-level planning and Integer Programming (IP) based robot-level planning. PIP-LLMs first decomposes the command by translating the command into a team-level PDDL problem and solves it to obtain a team-level plan, abstracting away robot assignment. Each team-level action represents a subtask to be finished by the team. Next, this plan is translated into a dependency graph representing the subtasks' dependency structure. Such a dependency graph is then used to guide the robot-level planning, in which each subtask node will be formulated as an IP-based task allocation problem, explicitly optimizing travel costs and workload while respecting robot capabilities and user-defined constraints. This separation of planning from assignment allows PIP-LLM to avoid the pitfalls of syntax-based decomposition and scale to larger teams. Experiments across diverse tasks show that PIP-LLM improves plan success rate, reduces maximum and average travel costs, and achieves better load balancing compared to state-of-the-art baselines.

cs.RO↗

arXiv2025

Compositional Coordination for Multi-Robot Teams with Large Language Models

Multi-robot coordination has traditionally relied on a mission-specific and expert-driven pipeline, where natural language mission descriptions are manually translated by domain experts into mathematical formulation, algorithm design, and executable code. This conventional process is labor-intensive, inaccessible to non-experts, and inflexible to changes in mission requirements. Here, we propose LAN2CB (Language to Collective Behavior), a novel framework that leverages large language models (LLMs) to streamline and generalize the multi-robot coordination pipeline. LAN2CB transforms natural language (NL) mission descriptions into executable Python code for multi-robot systems through two core modules: (1) Mission Analysis, which parses mission descriptions into behavior trees, and (2) Code Generation, which leverages the behavior tree and a structured knowledge base to generate robot control code. We further introduce a dataset of natural language mission descriptions to support development and benchmarking. Experiments in both simulation and real-world environments demonstrate that LAN2CB enables robust and flexible multi-robot coordination from natural language, significantly reducing manual engineering effort and supporting broad generalization across diverse mission types. Website: https://sites.google.com/view/lan-cb

cs.RO↗

arXiv2025

Real-Time Glass Detection and Reprojection using Sensor Fusion Onboard Aerial Robots

Autonomous aerial robots are increasingly being deployed in real-world scenarios, where transparent obstacles present significant challenges to reliable navigation and mapping. These materials pose a unique problem for traditional perception systems because they lack discernible features and can cause conventional depth sensors to fail, leading to inaccurate maps and potential collisions. To ensure safe navigation, robots must be able to accurately detect and map these transparent obstacles. Existing methods often rely on large, expensive sensors or algorithms that impose high computational burdens, making them unsuitable for low Size, Weight, and Power (SWaP) robots. In this work, we propose a novel and computationally efficient framework for detecting and mapping transparent obstacles onboard a sub-300g quadrotor. Our method fuses data from a Time-of-Flight (ToF) camera and an ultrasonic sensor with a custom, lightweight 2D convolution model. This specialized approach accurately detects specular reflections and propagates their depth into corresponding empty regions of the depth map, effectively rendering transparent obstacles visible. The entire pipeline operates in real-time, utilizing only a small fraction of a CPU core on an embedded processor. We validate our system through a series of experiments in both controlled and real-world environments, demonstrating the utility of our method through experiments where the robot maps indoor environments containing glass. Our work is, to our knowledge, the first of its kind to demonstrate a real-time, onboard transparent obstacle mapping system on a low-SWaP quadrotor using only the CPU.

cs.RO↗

arXiv2025

Distilling On-device Language Models for Robot Planning with Minimal Human Intervention

Large language models (LLMs) provide robots with powerful contextual reasoning abilities and a natural human interface. Yet, current LLM-enabled robots typically depend on cloud-hosted models, limiting their usability in environments with unreliable communication infrastructure, such as outdoor or industrial settings. We present PRISM, a framework for distilling small language model (SLM)-enabled robot planners that run on-device with minimal human supervision. Starting from an existing LLM-enabled planner, PRISM automatically synthesizes diverse tasks and environments, elicits plans from the LLM, and uses this synthetic dataset to distill a compact SLM as a drop-in replacement of the source model. We apply PRISM to three LLM-enabled planners for mapping and exploration, manipulation, and household assistance, and we demonstrate that PRISM improves the performance of Llama-3.2-3B from 10-20% of GPT-4o's performance to over 93% - using only synthetic data. We further demonstrate that the distilled planners generalize across heterogeneous robotic platforms (ground and aerial) and diverse environments (indoor and outdoor). We release all software, trained models, and datasets at https://zacravichandran.github.io/PRISM.

cs.RO↗

arXiv2025

RT-GuIDE: Real-Time Gaussian Splatting for Information-Driven Exploration

We propose a framework for active mapping and exploration that leverages Gaussian splatting for constructing dense maps. Further, we develop a GPU-accelerated motion planning algorithm that can exploit the Gaussian map for real-time navigation. The Gaussian map constructed onboard the robot is optimized for both photometric and geometric quality while enabling real-time situational awareness for autonomy. We show through viewpoint selection experiments that our method yields comparable Peak Signal-to-Noise Ratio (PSNR) and similar reconstruction error to state-of-the-art approaches, while being orders of magnitude faster to compute. In closed-loop physics-based simulation and real-world experiments, our algorithm achieves better map quality (at least 0.8dB higher PSNR and more than 16% higher geometric reconstruction accuracy) than maps constructed by a state-of-the-art method, enabling semantic segmentation using off-the-shelf open-set models. Experiment videos and more details can be found on our project page: https://tyuezhan.github.io/RT GuIDE/

cs.RO↗

arXiv2025

SlideSLAM: Sparse, Lightweight, Decentralized Metric-Semantic SLAM for Multi-Robot Navigation

This paper develops a real-time decentralized metric-semantic SLAM algorithm that enables a heterogeneous robot team to collaboratively construct object-based metric-semantic maps. The proposed framework integrates a data-driven front-end for instance segmentation from either RGBD cameras or LiDARs and a custom back-end for optimizing robot trajectories and object landmarks in the map. To allow multiple robots to merge their information, we design semantics-driven place recognition algorithms that leverage the informativeness and viewpoint invariance of the object-level metric-semantic map for inter-robot loop closure detection. A communication module is designed to track each robot's observations and those of other robots whenever communication links are available. The framework supports real-time, decentralized operation onboard the robots and has been integrated with three types of aerial and ground platforms. We validate its effectiveness through experiments in both indoor and outdoor environments, as well as benchmarks on public datasets and comparisons with existing methods. The framework is open-sourced and suitable for both single-agent and multi-robot real-time metric-semantic SLAM applications. The code is available at: https://github.com/KumarRobotics/SLIDE_SLAM.

cs.RO↗

arXiv2025

DroneFL: Federated Learning for Multi-UAV Visual Target Tracking

Multi-robot target tracking is a fundamental problem that requires coordinated monitoring of dynamic entities in applications such as precision agriculture, environmental monitoring, disaster response, and security surveillance. While Federated Learning (FL) has the potential to enhance learning across multiple robots without centralized data aggregation, its use in multi-Unmanned Aerial Vehicle (UAV) target tracking remains largely underexplored. Key challenges include limited onboard computational resources, significant data heterogeneity in FL due to varying targets and the fields of view, and the need for tight coupling between trajectory prediction and multi-robot planning. In this paper, we introduce DroneFL, the first federated learning framework specifically designed for efficient multi-UAV target tracking. We design a lightweight local model to predict target trajectories from sensor inputs, using a frozen YOLO backbone and a shallow transformer for efficient onboard training. The updated models are periodically aggregated in the cloud for global knowledge sharing. To alleviate the data heterogeneity that hinders FL convergence, DroneFL introduces a position-invariant model architecture with altitude-based adaptive instance normalization. Finally, we fuse predictions from multiple UAVs in the cloud and generate optimal trajectories that balance target prediction accuracy and overall tracking performance. Our results show that DroneFL reduces prediction error by 6%-83% and tracking distance by 0.4%-4.6% compared to a distributed non-FL framework. In terms of efficiency, DroneFL runs in real time on a Raspberry Pi 5 and has on average just 1.56 KBps data rate to the cloud.

cs.RO↗

arXiv2025

Machine learning meets Singular Optics II: Single-pixel Detection of Structured Light

Structured light beams, including Laguerre-Gaussian (LG), Hermite-Gaussian (HG), and perfect vortex (PV) spatial modes, have been at the forefront of modern optics due to their potential in communications, metrology, and sensing. Traditional recognition methods often demand complex alignments and high-resolution imaging. Speckle-learned recognition (SLR) has emerged as a powerful alternative, exploiting the spatio-temporal speckle fields generated by light-diffuser interactions. This paper builds upon the earlier report: Machine Learning Meets Singular Optics (Proc. SPIE 12938, 2024), which demonstrated structured light recognition using 2D speckle images in both on-axis and off-axis channels captured in the spatial domain. In the present work, the recognition framework is advanced by employing 1D speckle information captured in the spatial and temporal domains. This paper reviews how the 2D spatial information of the structured light is mapped on 1D speckle arrays captured in space and 1D temporal speckle fluctuations recorded in time. The 1D speckle arrays captured in the spatial domain have successfully recognised the parent structured light beams with accuracy exceeding 94%, even by employing 1/nth of the 2D speckle data. More recently, 2D spatial information of structured light beams has been mapped onto temporal speckle sequences recorded by a single-pixel detector in the temporal domain. This study highlights the accuracy exceeding 96% across various structured light families, with resilience to turbulence and modal degeneracy. These advances establish scalable, alignment-free, and low-latency recognition architectures suitable for optical communication, sensing, and quantum technologies.

physics.optics↗

arXiv2025

MAST: Multi-Agent Spatial Transformer for Learning to Collaborate

This article presents a novel multi-agent spatial transformer (MAST) for learning communication policies in large-scale decentralized and collaborative multi-robot systems (DC-MRS). Challenges in collaboration in DC-MRS arise from: (i) partial observable states as robots make only localized perception, (ii) limited communication range with no central server, and (iii) independent execution of actions. The robots need to optimize a common task-specific objective, which, under the restricted setting, must be done using a communication policy that exhibits the desired collaborative behavior. The proposed MAST is a decentralized transformer architecture that learns communication policies to compute abstract information to be shared with other agents and processes the received information with the robot's own observations. The MAST extends the standard transformer with new positional encoding strategies and attention operations that employ windowing to limit the receptive field for MRS. These are designed for local computation, shift-equivariance, and permutation equivariance, making it a promising approach for DC-MRS. We demonstrate the efficacy of MAST on decentralized assignment and navigation (DAN) and decentralized coverage control. Efficiently trained using imitation learning in a centralized setting, the decentralized MAST policy is robust to communication delays, scales to large teams, and performs better than the baselines and other learning-based approaches.

cs.RO↗

arXiv2025

Online Multi-Robot Coordination and Cooperation with Task Precedence Relationships

We propose a new formulation for the multi-robot task allocation problem that incorporates (a) complex precedence relationships between tasks, (b) efficient intra-task coordination, and (c) cooperation through the formation of robot coalitions. A task graph specifies the tasks and their relationships, and a set of reward functions models the effects of coalition size and preceding task performance. Maximizing task rewards is NP-hard; hence, we propose network flow-based algorithms to approximate solutions efficiently. A novel online algorithm performs iterative re-allocation, providing robustness to task failures and model inaccuracies to achieve higher performance than offline approaches. We comprehensively evaluate the algorithms in a testbed with random missions and reward functions and compare them to a mixed-integer solver and a greedy heuristic. Additionally, we validate the overall approach in an advanced simulator, modeling reward functions based on realistic physical phenomena and executing the tasks with realistic robot dynamics. Results establish efficacy in modeling complex missions and efficiency in generating high-fidelity task plans while leveraging task relationships.

cs.RO↗

arXiv2025

SPAR: Scalable LLM-based PDDL Domain Generation for Aerial Robotics

We investigate the problem of automatic domain generation for the Planning Domain Definition Language (PDDL) using Large Language Models (LLMs), with a particular focus on unmanned aerial vehicle (UAV) tasks. Although PDDL is a widely adopted standard in robotic planning, manually designing domains for diverse applications such as surveillance, delivery, and inspection is labor-intensive and error-prone, which hinders adoption and real-world deployment. To address these challenges, we propose SPAR, a framework that leverages the generative capabilities of LLMs to automatically produce valid, diverse, and semantically accurate PDDL domains from natural language input. To this end, we first introduce a systematically formulated and validated UAV planning dataset, consisting of ground-truth PDDL domains and associated problems, each paired with detailed domain and action descriptions. Building on this dataset, we design a prompting framework that generates high-quality PDDL domains from language input. The generated domains are evaluated through syntax validation, executability, feasibility, and interpretability. Overall, this work demonstrates that LLMs can substantially accelerate the creation of complex planning domains, providing a reproducible dataset and evaluation pipeline that enables application experts without prior experience to leverage it for practical tasks and advance future research in aerial robotics and automated planning.

cs.RO↗

arXiv2025

Coupled Infrared Imaging and Multiphysics Modeling to Predict Three-Dimensional Thermal Characteristics during Selective Laser Melting

Laser heating during additive manufacturing (AM) induces extreme and transient thermal conditions which critically influence the microstructure evolution and mechanical properties of the resulting component. However, accurately resolving these conditions with sufficient spatiotemporal accuracy remains a central challenge. We demonstrate a unique approach that couples high-speed infrared imaging, during selective laser melting of MAR-M247, with a transient three-dimensional (3D) multiphysics simulation to reconstruct the dynamic sub-surface temperature distribution of the melt pool. This integrated framework enables the estimation of experimentally-validated, 3D solidification conditions-including solidification velocities and cooling rates-at the solid-liquid interface while also significantly lowering computational cost. By quantifying solidification conditions, we predict variations in microstructure size and orientation driven by laser processing parameters and validate them with ex situ scanning electron microscopy and electron backscatter diffraction maps. Our findings substantiate that an integrated experimental-computational approach is crucial to realize in situ prediction and optimization of microstructures in commercial AM.

cond-mat.mtrl-sci↗

arXiv2025

A Variational Physics-Informed Neural Network Framework Using Petrov-Galerkin Method for Solving Singularly Perturbed Boundary Value Problems

This work proposes a Variational Physics-Informed Neural Network (VPINN) framework that integrates the Petrov-Galerkin formulation with deep neural networks (DNNs) for solving one-dimensional singularly perturbed boundary value problems (BVPs) and parabolic partial differential equations (PDEs) involving one or two small parameters. The method adopts a nonlinear approximation in which the trial space is defined by neural network functions, while the test space is constructed from hat functions. The weak formulation is constructed using localized test functions, with interface penalty terms introduced to enhance numerical stability and accurately capture boundary layers. Dirichlet boundary conditions are imposed via hard constraints, and source terms are computed using automatic differentiation. Numerical experiments on benchmark problems demonstrate the effectiveness of the proposed method, showing significantly improved accuracy in both the $L_2$ and maximum norms compared to the standard VPINN approach for one-dimensional singularly perturbed differential equations (SPDEs).

math.NA↗

arXiv2025

Resilient Multi-Robot Target Tracking with Sensing and Communication Danger Zones

Multi-robot collaboration for target tracking in adversarial environments poses significant challenges, including system failures, dynamic priority shifts, and other unpredictable factors. These challenges become even more pronounced when the environment is unknown. In this paper, we propose a resilient coordination framework for multi-robot, multi-target tracking in environments with unknown sensing and communication danger zones. We consider scenarios where failures caused by these danger zones are probabilistic and temporary, allowing robots to escape from danger zones to minimize the risk of future failures. We formulate this problem as a nonlinear optimization with soft chance constraints, enabling real-time adjustments to robot behaviors based on varying types of dangers and failures. This approach dynamically balances target tracking performance and resilience, adapting to evolving sensing and communication conditions in real-time. To validate the effectiveness of the proposed method, we assess its performance across various tracking scenarios, benchmark it against methods without resilient adaptation and collaboration, and conduct several real-world experiments.

cs.RO↗

arXiv2025

Van der Waals injection-molded crystals

Shaping low-dimensional crystals into precise geometries with low disorder is an outstanding challenge. Here, we present a method to grow single crystals of arbitrary geometry within van der Waals (vdW) materials. By injecting molten material between atomically-flat vdW layers within an SiO2 mold, we produce ultraflat and thin crystals of bismuth, tin, and indium that are shaped as hallbars, rings, and nanowires. The crystals are grown fully encapsulated in hexagonal boron nitride, a vdW material, providing protection from oxidation. Varying the depth of the mold allows us to control the crystal thickness from ten to a hundred nanometers. Structural measurements demonstrate large single-crystals encompassing the entire mold geometry, while transport measurements show reduced disorder scattering. This approach offers a means to produce complex single-crystal nanostructures without the disorder introduced by post-growth nanofabrication.

cond-mat.mtrl-sci↗

arXiv2025

3D Active Metric-Semantic SLAM

In this letter, we address the problem of exploration and metric-semantic mapping of multi-floor GPS-denied indoor environments using Size Weight and Power (SWaP) constrained aerial robots. Most previous work in exploration assumes that robot localization is solved. However, neglecting the state uncertainty of the agent can ultimately lead to cascading errors both in the resulting map and in the state of the agent itself. Furthermore, actions that reduce localization errors may be at direct odds with the exploration task. We propose a framework that balances the efficiency of exploration with actions that reduce the state uncertainty of the agent. In particular, our algorithmic approach for active metric-semantic SLAM is built upon sparse information abstracted from raw problem data, to make it suitable for SWaP-constrained robots. Furthermore, we integrate this framework within a fully autonomous aerial robotic system that achieves autonomous exploration in cluttered, 3D environments. From extensive real-world experiments, we showed that by including Semantic Loop Closure (SLC), we can reduce the robot pose estimation errors by over 90% in translation and approximately 75% in yaw, and the uncertainties in pose estimates and semantic maps by over 70% and 65%, respectively. Although discussed in the context of indoor multi-floor exploration, our system can be used for various other applications, such as infrastructure inspection and precision agriculture where reliable GPS data may not be available.

cs.RO↗