Masood Dehghan — accepted AI-conference papers

2023

Learning State Conditioned Linear Mappings for Low-Dimensional Control of Robotic Manipulators

Michael Przystupa, Kerrick Johnstonbaugh, Zichen Zhang, Laura Petrich, Masood Dehghan, Faezeh Haghverd +1

ICRA 2023poster

Identifying an appropriate task space can simplify solving robotic manipulation problems. One solution is deploying control algorithms in a learned low-dimensional action space. Linear and nonlinear action mapping methods have trade-offs between simplicity and the ability to express motor commands o…

Cited by 3 Source ↗Scholar ↗

2023

Managing Temporal Resolution in Continuous Value Estimation: A Fundamental Trade-off

Zichen Zhang, Johannes Kirschner, Junxi Zhang, Francesco Zanini, Alex Ayoub, Masood Dehghan +1

NeurIPS 2023poster

A default assumption in reinforcement learning (RL) and optimal control is that observations arrive at discrete time points on a fixed clock cycle. Yet, many applications involve continuous-time systems where the time discretization, in principle, can be managed. The impact of time discretization on…

Cited by 4 Source ↗PDF ↗Scholar ↗

2022

A Quantitative Analysis of Activities of Daily Living: Insights into Improving Functional Independence with Assistive Robotics

Laura Petrich, Jun Jin, Masood Dehghan, Martin Jagersand

ICRA 2022poster

Wheelchair-mounted robotic manipulators have the potential to help the elderly and individuals living with disabilities carry out their activities of daily living (ADLs) independently. Robotics researchers focus on assistive tasks from the perspective of various control schemes and motion types, whe…

Cited by 24 Source ↗Scholar ↗

2021

Analyzing Neural Jacobian Methods in Applications of Visual Servoing and Kinematic Control

Michael Przystupa, Masood Dehghan, Martin Jagersand, A. Rupam Mahmood

ICRA 2021poster

Designing adaptable control laws that can transfer between different robots is a challenge because of kinematic and dynamic differences, as well as in scenarios where external sensors are used. In this work, we empirically investigate a neural networks ability to approximate the Jacobian matrix for…

Cited by 8 Source ↗code ↗Scholar ↗

2020

A Geometric Perspective on Visual Imitation Learning

Jun Jin, Laura Petrich, Masood Dehghan, Martin Jagersand

IROS 2020poster

We consider the problem of visual imitation learning without human kinesthetic teaching or teleoperation, nor access to an interactive reinforcement learning training environment. We present a geometric perspective to this problem where geometric feature correspondences are learned from one training…

Cited by 22 Source ↗Scholar ↗

2020

Understanding Contexts Inside Robot and Human Manipulation Tasks through Vision-Language Model and Ontology System in Video Streams

Chen Jiang, Masood Dehghan, Martin Jagersand

IROS 2020poster

Manipulation tasks in daily life, such as pouring water, unfold through human intentions. Being able to process contextual knowledge from these Activities of Daily Living (ADLs) over time can help us understand manipulation intentions, which are essential for an intelligent robot to transition smoot…

Cited by 11 Source ↗Scholar ↗

2020

Visual Geometric Skill Inference by Watching Human Demonstration

Jun Jin, Laura Petrich, Zichen Zhang, Masood Dehghan, Martin Jagersand

ICRA 2020poster

We study the problem of learning manipulation skills from human demonstration video by inferring the association relationships between geometric features. Motivation for this work stems from the observation that humans perform eye-hand coordination tasks by using geometric primitives to define a tas…

Cited by 12 Source ↗Scholar ↗

2019

BASNet: Boundary-Aware Salient Object Detection

Xuebin Qin, Zichen Zhang, Chenyang Huang, Chao Gao, Masood Dehghan, Martin Jagersand

CVPR 2019poster

Deep Convolutional Neural Networks have been adopted for salient object detection and achieved the state-of-the-art performance. Most of the previous works however focus on region accuracy but not on the boundary quality. In this paper, we propose a predict-refine architecture, BASNet, and a new hyb…

Cited by 1782 PDF ↗code ↗Scholar ↗

2019

Online Object and Task Learning via Human Robot Interaction

Masood Dehghan, Zichen Zhang, Mennatullah Siam, Jun Jin, Laura Petrich, Martin Jagersand

ICRA 2019poster

This work describes the development of a robotic system that acquires knowledge incrementally through human interaction where new objects and motions are taught on the fly. The robotic system developed was one of the five finalists in the KUKA Innovation Award competition and demonstrated during the…

Cited by 32 Source ↗Scholar ↗

2019

Robot eye-hand coordination learning by watching human demonstrations: a task function approximation approach

Jun Jin, Laura Petrich, Masood Dehghan, Zichen Zhang, Martin Jagersand

ICRA 2019poster

We present a robot eye-hand coordination learning method that can directly learn visual task specification by watching human demonstrations. Task specification is represented as a task function, which is learned using inverse reinforcement learning(IRL [1]) by inferring a reward model from state tra…

Cited by 19 Source ↗Scholar ↗

2018

Real-Time Edge Template Tracking via Homography Estimation

Xuebin Qin, Shida He, Zichen Zhang, Masood Dehghan, Jun Jin, Martin Jagersand

IROS 2018poster

In this paper, we propose a novel real-time method for tracking planar edge templates. This method tracks an edge template by estimating its homography transformations with respect to the sampled edge pixels detected from the incoming frames. Particularly, we define a cost function based on a new fe…

Cited by 1 Source ↗Scholar ↗

2017

Flexible virtual fixture interface for path specification in tele-manipulation

Camilo Perez Quintero, Masood Dehghan, Oscar Ramirez, Marcelo H. Ang, Martin Jagersand

ICRA 2017poster

We present the design and implementation of a flexible force-vision-based interface; allowing local operators to visually specify a path constraint to a remote robot manipulator in an on-line fashion during the teleoperation. Using bilateral and unilateral configurations, we compare our system to di…

Cited by 44 Source ↗Scholar ↗

2017

Real-time salient closed boundary tracking via line segments perceptual grouping

Xuebin Qin, Shida He, Camilo Perez Quintero, Abhineet Singh, Masood Dehghan, Martin Jagersand

IROS 2017poster

This paper presents a novel real-time method for tracking salient closed boundaries from video image sequences. This method operates on a set of straight line segments that are produced by line detection. The tracking scheme is coherently integrated into a perceptual grouping framework in which the…

Cited by 13 Source ↗Scholar ↗