Vijay Kumar
YOU?
Author Swipe
View article: Quad-LCD: Layered Control Decomposition Enables Actuator-Feasible Quadrotor Trajectory Planning
Quad-LCD: Layered Control Decomposition Enables Actuator-Feasible Quadrotor Trajectory Planning Open
In this work, we specialize contributions from prior work on data-driven trajectory generation for a quadrotor system with motor saturation constraints. When motors saturate in quadrotor systems, there is an ``uncontrolled drift" of the ve…
View article: Air-Ground Collaboration for Language-Specified Missions in Unknown Environments
Air-Ground Collaboration for Language-Specified Missions in Unknown Environments Open
As autonomous robotic systems become increasingly mature, users will want to specify missions at the level of intent rather than in low-level detail. Language is an expressive and intuitive medium for such mission specification. However, r…
View article: ADMM-MCBF-LCA: A Layered Control Architecture for Safe Real-Time Navigation
ADMM-MCBF-LCA: A Layered Control Architecture for Safe Real-Time Navigation Open
We consider the problem of safe real-time navigation of a robot in a dynamic environment with moving obstacles of arbitrary smooth geometries and input saturation constraints. We assume that the robot detects and models nearby obstacle bou…
View article: SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environments
SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environments Open
As robots become increasingly capable, users will want to describe high-level missions and have robots infer the relevant details. Because pre-built maps are difficult to obtain in many realistic settings, accomplishing such missions will …
View article: AgriNeRF: Neural Radiance Fields for Agriculture in Challenging Lighting Conditions
AgriNeRF: Neural Radiance Fields for Agriculture in Challenging Lighting Conditions Open
Neural Radiance Fields (NeRFs) have shown significant promise in 3D scene reconstruction and novel view synthesis. In agricultural settings, NeRFs can serve as digital twins, providing critical information about fruit detection for yield e…
View article: Resilient Multi-Robot Target Tracking with Sensing and Communication Danger Zones
Resilient Multi-Robot Target Tracking with Sensing and Communication Danger Zones Open
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 …
View article: Constrained Learning for Decentralized Multi-Objective Coverage Control
Constrained Learning for Decentralized Multi-Objective Coverage Control Open
The multi-objective coverage control problem requires a robot swarm to collaboratively provide sensor coverage to multiple heterogeneous importance density fields IDFs simultaneously. We pose this as an optimization problem with constraint…
View article: Constraint-Aware Intent Estimation for Dynamic Human-Robot Object Co-Manipulation
Constraint-Aware Intent Estimation for Dynamic Human-Robot Object Co-Manipulation Open
Constraint-aware estimation of human intent is essential for robots to physically collaborate and interact with humans. Further, to achieve fluid collaboration in dynamic tasks intent estimation should be achieved in real-time. In this pap…
View article: An active learning enhanced data programming (ActDP) framework for ECG time series
An active learning enhanced data programming (ActDP) framework for ECG time series Open
Supervised machine learning learns a mapping from input data to output labels, based on the patterns and relationships present in a huge labelled training data.Getting labelled data generally requires a substantial allocation of resources …
View article: SlideSLAM: Sparse, Lightweight, Decentralized Metric-Semantic SLAM for Multi-Robot Navigation
SlideSLAM: Sparse, Lightweight, Decentralized Metric-Semantic SLAM for Multi-Robot Navigation Open
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 …
View article: Sense (and) the city: From Internet of Things sensors and open data platforms to urban observatories
Sense (and) the city: From Internet of Things sensors and open data platforms to urban observatories Open
Digitalisation and the Internet of Things (IoT) help city councils improve services, increase productivity and reduce costs. City‐scale monitoring of traffic and pollution enables the development of insights into low‐air quality areas and …
View article: A Study of Work-life Integration for Women Entrepreneurs
A Study of Work-life Integration for Women Entrepreneurs Open
There is no doubt that women's responsibilities towards the family are important. If we talk about a woman entrepreneur, then this responsibility becomes even greater because she has to balance her work or enterprise and the work of her fa…
View article: Challenges and Opportunities for Large-Scale Exploration with Air-Ground Teams using Semantics
Challenges and Opportunities for Large-Scale Exploration with Air-Ground Teams using Semantics Open
One common and desirable application of robots is exploring potentially hazardous and unstructured environments. Air-ground collaboration offers a synergistic approach to addressing such exploration challenges. In this paper, we demonstrat…
View article: Multi-Robot Target Tracking with Sensing and Communication Danger Zones
Multi-Robot Target Tracking with Sensing and Communication Danger Zones Open
Multi-robot target tracking finds extensive applications in different scenarios, such as environmental surveillance and wildfire management, which require the robustness of the practical deployment of multi-robot systems in uncertain and d…
View article: An Active Perception Game for Robust Information Gathering
An Active Perception Game for Robust Information Gathering Open
Active perception approaches select future viewpoints by using some estimate of the information gain. An inaccurate estimate can be detrimental in critical situations, e.g., locating a person in distress. However the true information gaine…
View article: Trajectory Optimization with Global Yaw Parameterization for Field-of-View Constrained Autonomous Flight
Trajectory Optimization with Global Yaw Parameterization for Field-of-View Constrained Autonomous Flight Open
Trajectory generation for quadrotors with limited field-of-view sensors has numerous applications such as aerial exploration, coverage, inspection, videography, and target tracking. Most previous works simplify the task of optimizing yaw t…
View article: Why Change Your Controller When You Can Change Your Planner: Drag-Aware Trajectory Generation for Quadrotor Systems
Why Change Your Controller When You Can Change Your Planner: Drag-Aware Trajectory Generation for Quadrotor Systems Open
Motivated by the increasing use of quadrotors for payload delivery, we consider a joint trajectory generation and feedback control design problem for a quadrotor experiencing aerodynamic wrenches. Unmodeled aerodynamic drag forces from car…
View article: LPAC: Learnable Perception-Action-Communication Loops with Applications to Coverage Control
LPAC: Learnable Perception-Action-Communication Loops with Applications to Coverage Control Open
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 communicatio…
View article: Almost Global Asymptotic Trajectory Tracking for Fully-Actuated Mechanical Systems on Homogeneous Riemannian Manifolds
Almost Global Asymptotic Trajectory Tracking for Fully-Actuated Mechanical Systems on Homogeneous Riemannian Manifolds Open
In this work, we address the design of tracking controllers that drive a\nmechanical system's state asymptotically towards a reference trajectory.\nMotivated by aerospace and robotics applications, we consider fully-actuated\nsystems evolv…
View article: Air-Ground Collaboration With SPOMP: Semantic Panoramic Online Mapping and Planning
Air-Ground Collaboration With SPOMP: Semantic Panoramic Online Mapping and Planning Open
Mapping and navigation have gone hand-in-hand since long before robots\nexisted. Maps are a key form of communication, allowing someone who has never\nbeen somewhere to nonetheless navigate that area successfully. In the context\nof multi-…
View article: Augmented Lagrangian Methods as Layered Control Architectures
Augmented Lagrangian Methods as Layered Control Architectures Open
For optimal control problems that involve planning and following a trajectory, two degree of freedom (2DOF) controllers are a ubiquitously used control architecture that decomposes the problem into a trajectory generation layer and a feedb…
View article: TreeScope: An Agricultural Robotics Dataset for LiDAR-Based Mapping of Trees in Forests and Orchards
TreeScope: An Agricultural Robotics Dataset for LiDAR-Based Mapping of Trees in Forests and Orchards Open
Data collection for forestry, timber, and agriculture currently relies on manual techniques which are labor-intensive and time-consuming. We seek to demonstrate that robotics offers improvements over these techniques and accelerate agricul…
View article: Deep Learning for Optimization of Trajectories for Quadrotors
Deep Learning for Optimization of Trajectories for Quadrotors Open
This paper presents a novel learning-based trajectory planning framework for quadrotors that combines model-based optimization techniques with deep learning. Specifically, we formulate the trajectory optimization problem as a quadratic pro…