Search Results for author: Ashish Kumar

Found 34 papers, 6 papers with code

Legs as Manipulator: Pushing Quadrupedal Agility Beyond Locomotion

no code implementations20 Mar 2023 Xuxin Cheng, Ashish Kumar, Deepak Pathak

Locomotion has seen dramatic progress for walking or running across challenging terrains.

Offline Robot Reinforcement Learning with Uncertainty-Guided Human Expert Sampling

no code implementations16 Dec 2022 Ashish Kumar, Ilya Kuzovkin

Although offline learning techniques can learn from data generated by a sub-optimal behavior agent, there is still an opportunity to improve the sample complexity of existing offline reinforcement learning algorithms by strategically introducing human demonstration data into the training process.

Q-Learning reinforcement-learning +1

Learning Visual Locomotion with Cross-Modal Supervision

no code implementations7 Nov 2022 Antonio Loquercio, Ashish Kumar, Jitendra Malik

In this work, we show how to learn a visual walking policy that only uses a monocular RGB camera and proprioception.

Learning a Single Near-hover Position Controller for Vastly Different Quadcopters

no code implementations19 Sep 2022 Dingqi Zhang, Antonio Loquercio, Xiangyu Wu, Ashish Kumar, Jitendra Malik, Mark W. Mueller

This paper proposes an adaptive near-hover position controller for quadcopters, which can be deployed to quadcopters of very different mass, size and motor constants, and also shows rapid adaptation to unknown disturbances during runtime.

Drone Controller

IterMiUnet: A lightweight architecture for automatic blood vessel segmentation

no code implementations2 Aug 2022 Ashish Kumar, R. K. Agrawal, Leve Joseph

Despite the success of Deep Learning-based models in this segmentation task, most of them are heavily parametrized and thus have limited use in practical applications.

An Open Source Interactive Visual Analytics Tool for Comparative Programming Comprehension

no code implementations29 Jul 2022 Ayush Kumar, Ashish Kumar, Aakanksha Prasad, Michael Burch, Shenghui Cheng, Klaus Mueller

We illustrate the usefulness of our tool by applying it to the eye movements of 216 programmers of multiple expertise levels that were collected during two code comprehension tasks.

Adapting Rapid Motor Adaptation for Bipedal Robots

no code implementations30 May 2022 Ashish Kumar, Zhongyu Li, Jun Zeng, Deepak Pathak, Koushil Sreenath, Jitendra Malik

In this work, we leverage recent advances in rapid adaptation for locomotion control, and extend them to work on bipedal robots.

Fairness-aware Configuration of Machine Learning Libraries

1 code implementation13 Feb 2022 Saeid Tizpaz-Niari, Ashish Kumar, Gang Tan, Ashutosh Trivedi

This paper investigates the parameter space of machine learning (ML) algorithms in aggravating or mitigating fairness bugs.

BIG-bench Machine Learning Fairness

Coupling Vision and Proprioception for Navigation of Legged Robots

no code implementations CVPR 2022 Zipeng Fu, Ashish Kumar, Ananye Agarwal, Haozhi Qi, Jitendra Malik, Deepak Pathak

A safety advisor module adds sensed unexpected obstacles to the occupancy map and environment-determined speed limits to the velocity command generator.

THz Band Channel Measurements and Statistical Modeling for Urban Microcellular Environments

no code implementations3 Dec 2021 Naveed A. Abbasi, Jorge Gomez-Ponce, Revanth Kondaveti, Ashish Kumar, Eshan Bhagat, Rakesh N S Rao, Shadi Abu-Surra, Gary Xu, Charlie Zhang, Andreas F. Molisch

The THz band (0. 1-10 THz) has attracted considerable attention for next-generation wireless communications, due to the large amount of available bandwidth that may be key to meet the rapidly increasing data rate requirements.

Generative Adversarial Network (GAN) and Enhanced Root Mean Square Error (ERMSE): Deep Learning for Stock Price Movement Prediction

no code implementations30 Nov 2021 Ashish Kumar, Abeer Alsadoon, P. W. C. Prasad, Salma Abdullah, Tarik A. Rashid, Duong Thu Hang Pham, Tran Quoc Vinh Nguyen

It seems that the proposed system concentrates on minimizing the root mean square error and processing time and improving the direction prediction accuracy, and provides a better result in the accuracy of the stock index.

Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robots

no code implementations25 Oct 2021 Zipeng Fu, Ashish Kumar, Jitendra Malik, Deepak Pathak

We demonstrate that learning to minimize energy consumption plays a key role in the emergence of natural locomotion gaits at different speeds in real quadruped robots.

Arbitrage-free pricing of CVA for cross-currency swap with wrong-way risk under stochastic correlation modeling framework

no code implementations13 Jul 2021 Ashish Kumar, Laszlo Markus, Norbert Hari

This effect is reflected in the results where the impact of stochastic correlation on calculated CVA is substantial when compared to the case when a high constant correlation is assumed between exposure and credit.

RMA: Rapid Motor Adaptation for Legged Robots

no code implementations8 Jul 2021 Ashish Kumar, Zipeng Fu, Deepak Pathak, Jitendra Malik

Successful real-world deployment of legged robots would require them to adapt in real-time to unseen scenarios like changing terrains, changing payloads, wear and tear.

Real Time Incremental Foveal Texture Mapping for Autonomous Vehicles

no code implementations16 Jan 2021 Ashish Kumar, James R. McBride, Gaurav Pandey

We propose an end-to-end real time framework to generate high resolution graphics grade textured 3D map of urban environment.

Autonomous Vehicles

Semi Supervised Deep Quick Instance Detection and Segmentation

no code implementations16 Jan 2021 Ashish Kumar, L. Behera

The framework can quickly and incrementally learn novel items in an online manner by real-time data acquisition and generating corresponding ground truths on its own.

Class-agnostic Object Detection object-detection +1

Shape Back-Projection In 3D Scenes

no code implementations16 Jan 2021 Ashish Kumar, L. Behera

In the overall process, first, shape histogram of a sample surface (e. g. planar) is computed, which captures the profile of surface normals around a point in form of a probability distribution.

Autonomous Vehicles Edge Detection

DeepMI: A Mutual Information Based Framework For Unsupervised Deep Learning of Tasks

no code implementations16 Jan 2021 Ashish Kumar, Laxmidhar Behera

The primary motivation behind this work is the limitation of the traditional loss functions for unsupervised learning of a given task.

Towards Deep Learning Assisted Autonomous UAVs for Manipulation Tasks in GPS-Denied Environments

no code implementations16 Jan 2021 Ashish Kumar, Mohit Vohra, Ravi Prakash, L. Behera

In this work, we present a pragmatic approach to enable unmanned aerial vehicle (UAVs) to autonomously perform highly complicated tasks of object pick and place.

MACE: Model Agnostic Concept Extractor for Explaining Image Classification Networks

1 code implementation3 Nov 2020 Ashish Kumar, Karan Sehgal, Prerna Garg, Vidhya Kamakshi, Narayanan C Krishnan

The current methods to explain the predictions of a pre-trained model rely on gradient information, often resulting in saliency maps that focus on the foreground object as a whole.

Classification General Classification +1

Domain Independent Unsupervised Learning to grasp the Novel Objects

no code implementations9 Jan 2020 Siddhartha Vibhu Pharswan, Mohit Vohra, Ashish Kumar, Laxmidhar Behera

In this paper, we present a novel unsupervised learning based algorithm for the selection of feasible grasp regions.

Learning Navigation Subroutines from Egocentric Videos

no code implementations29 May 2019 Ashish Kumar, Saurabh Gupta, Jitendra Malik

We demonstrate our proposed approach in context of navigation, and show that we can successfully learn consistent and diverse visuomotor subroutines from passive egocentric videos.

Pseudo Label

FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network

1 code implementation NeurIPS 2018 Aditya Kusupati, Manish Singh, Kush Bhatia, Ashish Kumar, Prateek Jain, Manik Varma

FastRNN addresses these limitations by adding a residual connection that does not constrain the range of the singular values explicitly and has only two extra scalar parameters.

Action Classification Language Modelling +3

Unified Graph based Multi-Cue Feature Fusion for Robust Visual Tracking

no code implementations16 Dec 2018 Kapil Sharma, Himanshu Ahuja, Ashish Kumar, Nipun Bansal, Gurjit Singh Walia

Extraction of complementary information from the object environment via multiple features and adaption to the target's appearance variations are the key problems of this work.

Object Tracking Outlier Detection +1

Visual Memory for Robust Path Following

no code implementations NeurIPS 2018 Ashish Kumar, Saurabh Gupta, David Fouhey, Sergey Levine, Jitendra Malik

Equipped with this abstraction, a second network observes the world and decides how to act to retrace the path under noisy actuation and a changing environment.

Resource-efficient Machine Learning in 2 KB RAM for the Internet of Things

1 code implementation ICML 2017 Ashish Kumar, Saurabh Goyal, Manik Varma

This paper develops a novel tree-based algorithm, called Bonsai, for efficient prediction on IoT devices – such as those based on the Arduino Uno board having an 8 bit ATmega328P microcontroller operating at 16 MHz with no native floating point support, 2 KB RAM and 32 KB read-only flash.

Action Classification BIG-bench Machine Learning

System and Methods for Converting Speech to SQL

no code implementations14 Aug 2013 Sachin Kumar, Ashish Kumar, Pinaki Mitra, Girish Sundaram

For conversion of speech into English text HTK and Julius tools have been used and for conversion of English text query into SQL query we have implemented a System which uses rule based translation to translate English Language Query into SQL Query.


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