Search Results for author: Swagat Kumar

Found 11 papers, 2 papers with code

Benchmarking Deep Reinforcement Learning Algorithms for Vision-based Robotics

no code implementations11 Jan 2022 Swagat Kumar, Hayden Sampson, Ardhendu Behera

To the best of our knowledge, such a benchmarking study is not available for the above two vision-based robotics problems making it a novel contribution in the field.

reinforcement-learning

Controlling an Inverted Pendulum with Policy Gradient Methods-A Tutorial

no code implementations17 May 2021 Swagat Kumar

This paper provides the details of implementing two important policy gradient methods to solve the inverted pendulum problem.

OpenAI Gym Policy Gradient Methods

Unsupervised Monocular Depth Estimation for Night-time Images using Adversarial Domain Feature Adaptation

1 code implementation ECCV 2020 Madhu Vankadari, Sourav Garg, Anima Majumder, Swagat Kumar, Ardhendu Behera

We propose to solve this problem by posing it as a domain adaptation problem where a network trained with day-time images is adapted to work for night-time images.

Depth Prediction Domain Adaptation +3

A Generalized Reinforcement Learning Algorithm for Online 3D Bin-Packing

no code implementations1 Jul 2020 Richa Verma, Aniruddha Singhal, Harshad Khadilkar, Ansuma Basumatary, Siddharth Nayak, Harsh Vardhan Singh, Swagat Kumar, Rajesh Sinha

We propose a Deep Reinforcement Learning (Deep RL) algorithm for solving the online 3D bin packing problem for an arbitrary number of bins and any bin size.

3D Bin Packing reinforcement-learning

Balancing a CartPole System with Reinforcement Learning -- A Tutorial

no code implementations8 Jun 2020 Swagat Kumar

In this paper, we provide the details of implementing various reinforcement learning (RL) algorithms for controlling a Cart-Pole system.

OpenAI Gym Q-Learning +1

Look No Deeper: Recognizing Places from Opposing Viewpoints under Varying Scene Appearance using Single-View Depth Estimation

1 code implementation20 Feb 2019 Sourav Garg, Madhu Babu V, Thanuja Dharmasiri, Stephen Hausler, Niko Suenderhauf, Swagat Kumar, Tom Drummond, Michael Milford

Visual place recognition (VPR) - the act of recognizing a familiar visual place - becomes difficult when there is extreme environmental appearance change or viewpoint change.

Robotics

UnDEMoN 2.0: Improved Depth and Ego Motion Estimation through Deep Image Sampling

no code implementations27 Nov 2018 Madhu Babu V, Swagat Kumar, Anima Majumder, Kaushik Das

In this paper, we provide an improved version of UnDEMoN model for depth and ego motion estimation from monocular images.

Depth Estimation Image Reconstruction +2

A Deeper Insight into the UnDEMoN: Unsupervised Deep Network for Depth and Ego-Motion Estimation

no code implementations27 Aug 2018 Madhu Babu V, Anima Majumder, Kaushik Das, Swagat Kumar

The proposed network is trained using unlabeled monocular stereo image pairs and is shown to provide superior performance in depth and ego-motion estimation compared to the existing state-of-the-art.

Depth Estimation Motion Estimation +1

An Occlusion Reasoning Scheme for Monocular Pedestrian Tracking in Dynamic Scenes

no code implementations25 Jan 2015 Sourav Garg, Swagat Kumar, Rajesh Ratnakaram, Prithwijit Guha

This paper looks into the problem of pedestrian tracking using a monocular, potentially moving, uncalibrated camera.

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