Search Results for author: Souma Chowdhury

Found 17 papers, 0 papers with code

Bigraph Matching Weighted with Learnt Incentive Function for Multi-Robot Task Allocation

no code implementations11 Mar 2024 Steve Paul, Nathan Maurer, Souma Chowdhury

Most real-world Multi-Robot Task Allocation (MRTA) problems require fast and efficient decision-making, which is often achieved using heuristics-aided methods such as genetic algorithms, auction-based methods, and bipartite graph matching methods.

Decision Making Graph Matching

Graph Learning-based Fleet Scheduling for Urban Air Mobility under Operational Constraints, Varying Demand & Uncertainties

no code implementations9 Jan 2024 Steve Paul, Jhoel Witter, Souma Chowdhury

This paper develops a graph reinforcement learning approach to online planning of the schedule and destinations of electric aircraft that comprise an urban air mobility (UAM) fleet operating across multiple vertiports.

Decoder Graph Learning +1

Fast Decision Support for Air Traffic Management at Urban Air Mobility Vertiports using Graph Learning

no code implementations17 Aug 2023 Prajit KrisshnaKumar, Jhoel Witter, Steve Paul, Hanvit Cho, Karthik Dantu, Souma Chowdhury

This paper provides a novel approach to this problem of Urban Air Mobility - Vertiport Schedule Management (UAM-VSM), which leverages graph reinforcement learning to generate decision-support policies.

Graph Learning Management +1

Learning Constrained Corner Node Trajectories of a Tether Net System for Space Debris Capture

no code implementations6 Jul 2023 Feng Liu, Achira Boonrath, Prajit KrisshnaKumar, Elenora M. Botta, Souma Chowdhury

The earth's orbit is becoming increasingly crowded with debris that poses significant safety risks to the operation of existing and new spacecraft and satellites.

Learning Robust Policies for Generalized Debris Capture with an Automated Tether-Net System

no code implementations11 Jan 2022 Chen Zeng, Grant Hecht, Prajit KrisshnaKumar, Raj K. Shah, Souma Chowdhury, Eleonora M. Botta

This tether-net system is subject to several sources of uncertainty in sensing and actuation that affect the performance of its net launch and closing control.

Learning to Solve Multi-Robot Task Allocation with a Covariant-Attention based Neural Architecture

no code implementations1 Jan 2021 Steve Paul, Payam Ghassemi, Souma Chowdhury

This paper presents a novel graph (reinforcement) learning method to solve an important class of multi-robot task allocation (MRTA) problems that involve tasks with deadlines, and robots with ferry range and payload constraints (thus requiring multiple tours per robot).

Combinatorial Optimization Graph Learning

Metamodel Based Forward and Inverse Design for Passive Vibration Suppression

no code implementations29 Jul 2020 Amir Behjat, Manaswin Oddiraju, Mohammad Ali Attarzadeh, Mostafa Nouh, Souma Chowdhury

Further novel contribution occurs through the development of an inverse modeling approach that can instantaneously produce the 1D metamaterial design with minimum mass for a given desired non-resonant frequency range.

Hybrid modeling: Applications in real-time diagnosis

no code implementations4 Mar 2020 Ion Matei, Johan de Kleer, Alexander Feldman, Rahul Rai, Souma Chowdhury

In this paper, we outline a novel hybrid modeling approach that combines machine learning inspired models and physics-based models to generate reduced-order models from high fidelity models.

BIG-bench Machine Learning

Informative Path Planning with Local Penalization for Decentralized and Asynchronous Swarm Robotic Search

no code implementations9 Jul 2019 Payam Ghassemi, Souma Chowdhury

Decentralized swarm robotic solutions to searching for targets that emit a spatially varying signal promise task parallelism, time efficiency, and fault tolerance.

Bayesian Optimization

Decentralized Dynamic Task Allocation in Swarm Robotic Systems for Disaster Response

no code implementations9 Jul 2019 Payam Ghassemi, David DePauw, Souma Chowdhury

Multiple robotic systems, working together, can provide important solutions to different real-world applications (e. g., disaster response), among which task allocation problems feature prominently.

Decision Making Disaster Response

Training Detection-Range-Frugal Cooperative Collision Avoidance Models for Quadcopters via Neuroevolution

no code implementations31 May 2019 Amir Behjat, Krushang Gabani, Souma Chowdhury

Neuroevolution, which uses evolutionary algorithms to simultaneously optimize the topology and weights of neural networks, is used as the learning method -- which operates over a set of sample approach scenarios.

Collision Avoidance Evolutionary Algorithms

Adaptive Model Refinement with Batch Bayesian Sampling for Optimization of Bio-inspired Flow Tailoring

no code implementations31 May 2019 Payam Ghassemi, Sumeet Sanjay Lulekar, Souma Chowdhury

This paper presents an advancement to an approach for model-independent surrogate-based optimization with adaptive batch sampling, known as Adaptive Model Refinement (AMR).

Bayesian Optimization

Adaptive Genomic Evolution of Neural Network Topologies (AGENT) for State-to-Action Mapping in Autonomous Agents

no code implementations17 Mar 2019 Amir Behjat, Sharat Chidambaran, Souma Chowdhury

Neuroevolution is a process of training neural networks (NN) through an evolutionary algorithm, usually to serve as a state-to-action mapping model in control or reinforcement learning-type problems.

Collision Avoidance Reinforcement Learning (RL)

Decentralized Task Allocation in Multi-Robot Systems via Bipartite Graph Matching Augmented with Fuzzy Clustering

no code implementations20 Jul 2018 Payam Ghassemi, Souma Chowdhury

The task planning problem is posed as a maximum-weighted matching of a bipartite graph, the solution of which using the blossom algorithm allows each robot to autonomously identify the optimal sequence of tasks it should undertake.

Clustering Disaster Response +3

Multi-criteria Evolution of Neural Network Topologies: Balancing Experience and Performance in Autonomous Systems

no code implementations20 Jul 2018 Sharat Chidambaran, Amir Behjat, Souma Chowdhury

Majority of Artificial Neural Network (ANN) implementations in autonomous systems use a fixed/user-prescribed network topology, leading to sub-optimal performance and low portability.

Cannot find the paper you are looking for? You can Submit a new open access paper.