Rahul Tallamraju
YOU?
Author Swipe
View article: SynthForge: Synthesizing High-Quality Face Dataset with Controllable 3D Generative Models
SynthForge: Synthesizing High-Quality Face Dataset with Controllable 3D Generative Models Open
Recent advancements in generative models have unlocked the capabilities to render photo-realistic data in a controllable fashion. Trained on the real data, these generative models are capable of producing realistic samples with minimal to …
View article: Semi-Supervised Domain Adaptation by Similarity based Pseudo-label Injection
Semi-Supervised Domain Adaptation by Similarity based Pseudo-label Injection Open
One of the primary challenges in Semi-supervised Domain Adaptation (SSDA) is the skewed ratio between the number of labeled source and target samples, causing the model to be biased towards the source domain. Recent works in SSDA show that…
View article: CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation
CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation Open
In this work, we propose CLUDA, a simple, yet novel method for performing unsupervised domain adaptation (UDA) for semantic segmentation by incorporating contrastive losses into a student-teacher learning paradigm, that makes use of pseudo…
View article: ViTOL: Vision Transformer for Weakly Supervised Object Localization
ViTOL: Vision Transformer for Weakly Supervised Object Localization Open
Weakly supervised object localization (WSOL) aims at predicting object locations in an image using only image-level category labels. Common challenges that image classification models encounter when localizing objects are, (a) they tend to…
View article: AirCapRL: Autonomous Aerial Human Motion Capture Using Deep Reinforcement Learning
AirCapRL: Autonomous Aerial Human Motion Capture Using Deep Reinforcement Learning Open
In this letter, we introduce a deep reinforcement learning (RL) based multi-robot formation controller for the task of autonomous aerial human motion capture (MoCap). We focus on vision-based MoCap, where the objective is to estimate the t…
View article: AirCapRL: Autonomous Aerial Human Motion Capture using Deep\n Reinforcement Learning
AirCapRL: Autonomous Aerial Human Motion Capture using Deep\n Reinforcement Learning Open
In this letter, we introduce a deep reinforcement learning (RL) based\nmulti-robot formation controller for the task of autonomous aerial human motion\ncapture (MoCap). We focus on vision-based MoCap, where the objective is to\nestimate th…
View article: Energy Conscious Over-actuated Multi-Agent Payload Transport Robot: Simulations and Preliminary Physical Validation
Energy Conscious Over-actuated Multi-Agent Payload Transport Robot: Simulations and Preliminary Physical Validation Open
In this work, we consider a multi-wheeled payload transport system. Each of the wheels can be selectively actuated. When they are not actuated, wheels are free moving and do not consume battery power. The payload transport system is modele…
View article: Energy Conscious Over-actuated Multi-Agent Payload Transport Robot:\n Simulations and Preliminary Physical Validation
Energy Conscious Over-actuated Multi-Agent Payload Transport Robot:\n Simulations and Preliminary Physical Validation Open
In this work, we consider a multi-wheeled payload transport system. Each of\nthe wheels can be selectively actuated. When they are not actuated, wheels are\nfree moving and do not consume battery power. The payload transport system is\nmod…
View article: Motion Planning for Multi-Mobile-Manipulator Payload Transport Systems
Motion Planning for Multi-Mobile-Manipulator Payload Transport Systems Open
In this paper, a kinematic motion planning algorithm for cooperative spatial payload manipulation is presented. A hierarchical approach is introduced to compute real-time collision-free motion plans for a formation of mobile manipulator ro…
View article: Multiple Drones driven Hexagonally Partitioned Area Exploration:\n Simulation and Evaluation
Multiple Drones driven Hexagonally Partitioned Area Exploration:\n Simulation and Evaluation Open
In this paper, we simulated a distributed, cooperative path planning\ntechnique for multiple drones (~200) to explore an unknown region (~10,000\nconnected units) in the presence of obstacles. The map of an unknown region is\ndynamically c…
View article: Multiple Drones driven Hexagonally Partitioned Area Exploration: Simulation and Evaluation
Multiple Drones driven Hexagonally Partitioned Area Exploration: Simulation and Evaluation Open
In this paper, we simulated a distributed, cooperative path planning technique for multiple drones (~200) to explore an unknown region (~10,000 connected units) in the presence of obstacles. The map of an unknown region is dynamically crea…
View article: Loosely Coupled Payload Transport System with Robot Replacement
Loosely Coupled Payload Transport System with Robot Replacement Open
In this work, we present an algorithm for robot replacement to increase the operational time of a multi-robot payload transport system. Our system comprises a group of nonholonomic wheeled mobile robots traversing on a known trajectory. We…
View article: Decentralized MPC based Obstacle Avoidance for Multi-Robot Target Tracking Scenarios
Decentralized MPC based Obstacle Avoidance for Multi-Robot Target Tracking Scenarios Open
In this work, we consider the problem of decentralized multi-robot target tracking and obstacle avoidance in dynamic environments. Each robot executes a local motion planning algorithm which is based on model predictive control (MPC). The …