no code implementations • 4 Apr 2024 • Anwesa Choudhuri, Girish Chowdhary, Alexander G. Schwing
To address these issues, we propose Open-World Video Instance Segmentation and Captioning (OW-VISCap), an approach to jointly segment, track, and caption previously seen or unseen objects in a video.
no code implementations • 15 Feb 2024 • Sathwik Tejaswi Madhusudhan, Girish Chowdhary
Our method achieves an accuracy of 88. 1% and 97 % during inference on the Comp Music Carnatic dataset and its 10 Raga subset respectively making it the state-of-the-art for the Raga recognition task.
no code implementations • 4 Feb 2024 • Junchen Deng, Samhita Marri, Jonathan Klein, Wojtek Pałubicki, Sören Pirk, Girish Chowdhary, Dominik L. Michels
Robotic harvesting has the potential to positively impact agricultural productivity, reduce costs, improve food quality, enhance sustainability, and to address labor shortage.
no code implementations • 6 Nov 2023 • Justin Wasserman, Girish Chowdhary, Abhinav Gupta, Unnat Jain
In the recent progress in embodied navigation and sim-to-robot transfer, modular policies have emerged as a de facto framework.
no code implementations • 26 Sep 2023 • Jiarui Sun, Yujie Fan, Chin-Chia Michael Yeh, Wei zhang, Girish Chowdhary
To address these issues, we propose Spatial-Temporal Masked Autoencoders (STMAE), an MTS forecasting framework that leverages masked autoencoders to enhance the performance of spatial-temporal baseline models.
no code implementations • 30 May 2023 • Jae Won Choi, Girish Chowdhary, Andrew C. Singer, Hari Vishnu, Amir Weiss, Gregory W. Wornell, Grant Deane
Underwater communication signals typically suffer from distortion due to motion-induced Doppler.
no code implementations • 21 May 2023 • Jiarui Sun, Girish Chowdhary
Stochastic Human Motion Prediction (HMP) aims to predict multiple possible upcoming pose sequences based on past human motion trajectories.
no code implementations • 8 May 2023 • Jiarui Sun, Girish Chowdhary
To address the problem, in this work we propose FreqMRN, a human motion prediction framework that takes into account both the kinematic structure of the human body and the temporal smoothness nature of motion.
Ranked #2 on
Human Pose Forecasting
on 3DPW
no code implementations • 22 Apr 2023 • Mateus V. Gasparino, Prabhat K. Mishra, Girish Chowdhary
We utilize a deep neural network (DNN) as an oracle in the underlying optimization problem of learning based MPC (LBMPC) to estimate unmatched uncertainties.
no code implementations • 27 Feb 2023 • Prabhat K. Mishra, Mateus V. Gasparino, Andres E. B. Velasquez, Girish Chowdhary
This paper presents a deep learning based model predictive control algorithm for control affine nonlinear discrete time systems with matched and bounded state-dependent uncertainties of unknown structure.
no code implementations • 5 Jan 2023 • Denis Osipychev, Dragos Margineantu, Girish Chowdhary
Remain Well Clear, keeping the aircraft away from hazards by the appropriate separation distance, is an essential technology for the safe operation of uncrewed aerial vehicles in congested airspace.
1 code implementation • CVPR 2023 • Anwesa Choudhuri, Girish Chowdhary, Alexander G. Schwing
We evaluate the proposed approach across three challenging tasks: video instance segmentation, multi-object tracking and segmentation, and video panoptic segmentation.
no code implementations • 7 Dec 2022 • Jiarui Sun, Mengting Gu, Chin-Chia Michael Yeh, Yujie Fan, Girish Chowdhary, Wei zhang
Node classification on dynamic graphs is challenging for two reasons.
1 code implementation • 21 Nov 2022 • Justin Wasserman, Karmesh Yadav, Girish Chowdhary, Abhinav Gupta, Unnat Jain
Realistic long-horizon tasks like image-goal navigation involve exploratory and exploitative phases.
1 code implementation • 25 Aug 2022 • Qingyun Wang, Manling Li, Hou Pong Chan, Lifu Huang, Julia Hockenmaier, Girish Chowdhary, Heng Ji
Goal-oriented generative script learning aims to generate subsequent steps to reach a particular goal, which is an essential task to assist robots or humans in performing stereotypical activities.
1 code implementation • 3 Apr 2022 • Tianchen Ji, Arun Narenthiran Sivakumar, Girish Chowdhary, Katherine Driggs-Campbell
The ability to detect such anomalous behaviors is a key component in modern robots to achieve high-levels of autonomy.
1 code implementation • 22 Mar 2022 • Mateus Valverde Gasparino, Arun Narenthiran Sivakumar, Yixiao Liu, Andres Eduardo Baquero Velasquez, Vitor Akihiro Hisano Higuti, John Rogers, Huy Tran, Girish Chowdhary
We present a self-supervised approach for learning to predict traversable paths for wheeled mobile robots that require good traction to navigate.
no code implementations • 10 Feb 2022 • Shivani Kamtikar, Samhita Marri, Benjamin Walt, Naveen Kumar Uppalapati, Girish Krishnan, Girish Chowdhary
For soft continuum arms, visual servoing is a popular control strategy that relies on visual feedback to close the control loop.
no code implementations • 3 Feb 2022 • Federico M. Zegers, Runhan Sun, Girish Chowdhary, Warren E. Dixon
Distributed state estimation is examined for a sensor network tasked with reconstructing a system's state through the use of a distributed and event-triggered observer.
1 code implementation • 4 Aug 2021 • Girish Joshi, Girish Chowdhary
In this paper, we present a Stochastic Deep Neural Network-based Model Reference Adaptive Control.
no code implementations • 6 Jul 2021 • Arun Narenthiran Sivakumar, Sahil Modi, Mateus Valverde Gasparino, Che Ellis, Andres Eduardo Baquero Velasquez, Girish Chowdhary, Saurabh Gupta
We describe a system for visually guided autonomous navigation of under-canopy farm robots.
no code implementations • 5 Jun 2021 • Aaron Havens, Girish Chowdhary
As deep learning becomes more prevalent for prediction and control of real physical systems, it is important that these overparameterized models are consistent with physically plausible dynamics.
no code implementations • 21 May 2021 • Michael McGuire, Chinmay Soman, Brian Diers, Girish Chowdhary
We report a correlation of 0. 67 between our automated pod counts and soybean yield.
no code implementations • 10 May 2021 • Girish Joshi, Girish Chowdhary
Efficient and robust policy transfer remains a key challenge for reinforcement learning to become viable for real-wold robotics.
no code implementations • 27 Mar 2021 • Erkan Kayacan, Joshua M. Peschel, Girish Chowdhary
This paper represents a novel online self-learning disturbance observer (SLDO) by benefiting from the combination of a type-2 neuro-fuzzy structure (T2NFS), feedback-error learning scheme and sliding mode control (SMC) theory.
no code implementations • 21 Mar 2021 • Zhongzhong Zhang, Erkan Kayacan, Benjamin Thompson, Girish Chowdhary
The robot, termed TerraSentia, is designed to automate the measurement of plant traits for efficient phenotyping as an alternative to manual measurements.
1 code implementation • ICCV 2021 • Anwesa Choudhuri, Girish Chowdhary, Alexander G. Schwing
In contrast, we formulate a global method for MOTS over the space of assignments rather than detections: First, we find all top-k assignments of objects detected and segmented between any two consecutive frames and develop a structured prediction formulation to score assignment sequences across any number of consecutive frames.
Multi-Object Tracking
Multi-Object Tracking and Segmentation
+4
1 code implementation • 15 Dec 2020 • Tianchen Ji, Sri Theja Vuppala, Girish Chowdhary, Katherine Driggs-Campbell
To achieve high-levels of autonomy, modern robots require the ability to detect and recover from anomalies and failures with minimal human supervision.
no code implementations • 25 Sep 2019 • Girish Joshi, Girish Chowdhary
Efficient and robust policy transfer remains a key challenge in reinforcement learning.
no code implementations • 25 Sep 2019 • Anwesa Choudhuri, Ashok Vardhan Makkuva, Ranvir Rana, Sewoong Oh, Girish Chowdhary, Alexander Schwing
%In fact, contrastive disentanglement and unsupervised recovery are often combined in that we seek additional variations that exhibit salient factors/properties.
1 code implementation • 18 Sep 2019 • Girish Joshi, Girish Chowdhary
We present a new neuroadaptive architecture: Deep Neural Network based Model Reference Adaptive Control (DMRAC).
no code implementations • 28 Jun 2019 • Xian Yeow Lee, Aaron Havens, Girish Chowdhary, Soumik Sarkar
Hence, it is imperative that RL agents deployed in real-life applications have the capability to detect and mitigate adversarial attacks in an online fashion.
no code implementations • 22 Jan 2018 • Girish Joshi, Girish Chowdhary
Many of the available techniques approach the transfer architecture as a method of speeding up the target task learning.
no code implementations • 11 Dec 2017 • Anay Pattanaik, Zhenyi Tang, Shuijing Liu, Gautham Bommannan, Girish Chowdhary
This paper proposes adversarial attacks for Reinforcement Learning (RL) and then improves the robustness of Deep Reinforcement Learning algorithms (DRL) to parameter uncertainties with the help of these attacks.
no code implementations • 14 Apr 2017 • Hossein Mohamadipanah, Mahdi Heydari, Girish Chowdhary
We present a new kernel-based algorithm for modeling evenly distributed multidimensional datasets that does not rely on input space sparsification.
no code implementations • NeurIPS 2016 • Hassan A. Kingravi, Harshal R. Maske, Girish Chowdhary
We consider the problem of estimating the latent state of a spatiotemporally evolving continuous function using very few sensor measurements.
no code implementations • 22 Nov 2016 • Harshal Maske, Emily Kieson, Girish Chowdhary, Charles Abramson
We explore beyond existing work on learning from demonstration by asking the question: Can robots learn to teach?, that is, can a robot autonomously learn an instructional policy from expert demonstration and use it to instruct or collaborate with humans in executing complex tasks in uncertain environments?