AIConfPaper
← Search

Punarjay Chakravarty

14 accepted papers

2023

DisPlacing Objects: Improving Dynamic Vehicle Detection via Visual Place Recognition under Adverse Conditions

Stephen Hausler, Sourav Garg, Punarjay Chakravarty, Shubham Shrivastava, Ankit Vora, Michael Milford
IROS 2023poster

Can knowing where you are assist in perceiving objects in your surroundings, especially under adverse weather and lighting conditions? In this work we investigate whether a prior map can be leveraged to aid in the detection of dynamic objects in a scene without the need for a 3D map or pixel-level m…

Cited by 6Source ↗Scholar ↗
2023

Locking On: Leveraging Dynamic Vehicle-Imposed Motion Constraints to Improve Visual Localization

Stephen Hausler, Sourav Garg, Punarjay Chakravarty, Shubham Shrivastava, Ankit Vora, Michael Milford
IROS 2023poster

Most 6-DoF localization and SLAM systems use static landmarks but ignore dynamic objects because they cannot be usefully incorporated into a typical pipeline. Where dynamic objects have been incorporated, typical approaches have attempted relatively sophisticated identification and localization of t…

Cited by 0Source ↗Scholar ↗
2023

RADIANT: Radar-Image Association Network for 3D Object Detection

Yunfei Long, Abhinav Kumar, Daniel Morris, Xiaoming Liu, Marcos Castro, Punarjay Chakravarty
AAAI 2023technical

As a direct depth sensor, radar holds promise as a tool to improve monocular 3D object detection, which suffers from depth errors, due in part to the depth-scale ambiguity. On the other hand, leveraging radar depths is hampered by difficulties in precisely associating radar returns with 3D estimates…

Cited by 31Source ↗PDF ↗code ↗Scholar ↗
2022

Improving Worst Case Visual Localization Coverage via Place-Specific Sub-Selection in Multi-Camera Systems

Stephen Hausler, Ming Xu, Sourav Garg, Punarjay Chakravarty, Shubham Shrivastava, Ankit Vora +1
RA-L 2022

6-DoF visual localization systems utilize principled approaches rooted in 3D geometry to perform accurate camera pose estimation of images to a map. Current techniques use hierarchical pipelines and learned 2D feature extractors to improve scalability and increase performance. However, despite gains

Cited by 10Source ↗Scholar ↗
2022

Localization of a Smart Infrastructure Fisheye Camera in a Prior Map for Autonomous Vehicles

Subodh Mishra, Armin Parchami, Enrique Corona, Punarjay Chakravarty, Ankit Vora, Devarth Parikh +1
ICRA 2022poster

This work presents a technique for localization of a smart infrastructure node, consisting of a fisheye camera, in a prior map. These cameras can detect objects that are outside the line of sight of the autonomous vehicles (AV) and send that information to AVs using V2X technology. However, in order…

Cited by 6Source ↗Scholar ↗
2022

Propagating State Uncertainty Through Trajectory Forecasting

Boris Ivanovic, Yifeng Lin, Shubham Shrivastava, Punarjay Chakravarty, Marco Pavone
ICRA 2022poster

Uncertainty pervades through the modern robotic autonomy stack, with nearly every component (e.g., sensors, detection, classification, tracking, behavior prediction) producing continuous or discrete probabilistic distributions. Trajectory forecasting, in particular, is surrounded by uncertainty as i…

Cited by 25Source ↗code ↗Scholar ↗
2022

Real-time Full-stack Traffic Scene Perception for Autonomous Driving with Roadside Cameras

Zhengxia Zou, Rusheng Zhang, Shengyin Shen, Gaurav Pandey, Punarjay Chakravarty, Armin Parchami +1
ICRA 2022poster

We propose a novel and pragmatic framework for traffic scene perception with roadside cameras. The proposed framework covers a full-stack of roadside perception pipeline for infrastructure-assisted autonomous driving, including object detection, object localization, object tracking, and multi-camera…

Cited by 50Source ↗Scholar ↗
2021

Full-Velocity Radar Returns by Radar-Camera Fusion

Yunfei Long, Daniel Morris, Xiaoming Liu, Marcos Castro, Punarjay Chakravarty, Praveen Narayanan
ICCV 2021poster

A distinctive feature of Doppler radar is the measurement of velocity in the radial direction for radar points. However, the missing tangential velocity component hampers object velocity estimation as well as temporal integration of radar sweeps in dynamic scenes. Recognizing that fusing camera with…

Cited by 28PDF ↗Scholar ↗
2021

Radar-Camera Pixel Depth Association for Depth Completion

Yunfei Long, Daniel Morris, Xiaoming Liu, Marcos Castro, Punarjay Chakravarty, Praveen Narayanan
CVPR 2021poster

While radar and video data can be readily fused at the detection level, fusing them at the pixel level is potentially more beneficial. This is also more challenging in part due to the sparsity of radar, but also because automotive radar beams are much wider than a typical pixel combined with a large…

Cited by 92PDF ↗code ↗Scholar ↗
2021

What My Motion tells me about Your Pose: A Self-Supervised Monocular 3D Vehicle Detector

Cédric Picron, Punarjay Chakravarty, Tom Roussel, Tinne Tuytelaars
ICRA 2021poster

The estimation of the orientation of an observed vehicle relative to an Autonomous Vehicle (AV) from monocular camera data is an important building block in estimating its 6 DoF pose. Current Deep Learning based solutions for placing a 3D bounding box around this observed vehicle are data hungry and…

Cited by 3Source ↗Scholar ↗
2020

Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data

Tim Salzmann, Boris Ivanovic, Punarjay Chakravarty, Marco Pavone
ECCV 2020poster

Reasoning about human motion is an important prerequisite to safe and socially-aware robotic navigation. As a result, multi-agent behavior prediction has become a core component of modern human-robot interactive systems, such as self-driving cars. While there exist many methods for trajectory foreca…

Cited by 1175Source ↗PDF ↗code ↗Scholar ↗
2019

GEN-SLAM: Generative Modeling for Monocular Simultaneous Localization and Mapping

Punarjay Chakravarty, Praveen Narayanan, Tom Roussel
ICRA 2019poster

We present a Deep Learning based system for the twin tasks of localization and obstacle avoidance essential to any mobile robot. Our system learns from conventional geometric SLAM, and outputs, using a single camera, the topological pose of the camera in an environment, and the depth map of obstacle…

Cited by 37Source ↗Scholar ↗
2017

CNN-based single image obstacle avoidance on a quadrotor

Punarjay Chakravarty, Klaas Kelchtermans, Tom Roussel, Stijn Wellens, Tinne Tuytelaars, Luc Van Eycken
ICRA 2017poster

This paper demonstrates the use of a single forward facing camera for obstacle avoidance on a quadrotor. We train a CNN for estimating depth from a single image. The depth map is then fed to a behaviour arbitration based control algorithm that steers the quadrotor away from obstacles. We conduct exp…

Cited by 106Source ↗Scholar ↗