Posts by Collection

portfolio

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

publications

A point and command interface for grasping unknown objects with robotic manipulators

Published in Politecnico di Milano, 2017

This is my masters thesis! It uses a graph-based RGBD image segmenter to implement a point-and-grasp interface for a ABB Yumi robot.

Recommended citation: Correia Marques, Joao Marcos. (2017). "A point and command interface for grasping unknown objects with robotic manipulators." Politecnico di Milano. https://www.politesi.polimi.it/bitstream/10589/137453/5/2017_12_Correia_Marques.pdf

Heuristic active learning for the prediction of epileptic seizures using single EEG channel

Published in 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2018

This paper investigates heuristics to enable active learning on EEG data to predict epileptic seizures

Recommended citation: Joao, M. C. Marques, et al. "Heuristic active learning for the prediction of epileptic seizures using single EEG channel." 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 2018. https://ieeexplore.ieee.org/abstract/document/8621506

Automatic summarization of technical documents in the oil and gas industry

Published in 8th Brazilian Conference on Intelligent Systems (BRACIS), 2019

This paper is about evaluating extractive summarization techniques to generate abstracts for papers in the field of oil-and-gas.

Recommended citation: Correia Marques, Joao Marcos, Cozman, Fabio G., Ferreira Dos Santos, Ismael H.. (2019). "Automatic summarization of technical documents in the oil and gas industry." 8th Brazilian Conference on Intelligent Systems (BRACIS). http://sites.poli.usp.br/p/fabio.cozman/Publications/Article/marques-cozman-santos-bracis2019.pdf

Optimized Coverage Planning for UV Surface Disinfection

Published in ICRA, 2021

This paper introduces an algorithm to compute the optimal (shortest) path for a UV light across an environment while guaranteeing that all surfaces get the necessary dose of UV radiation for disinfection - and evaluates different robot designs for this task.

Recommended citation: Marques, Joao Marcos Correia, et al. "Optimized coverage planning for UV surface disinfection." 2021 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2021. https://arxiv.org/abs/2103.14137

Commodity Telepresence with the AvaTRINA Nursebot in the ANA Avatar XPRIZE Semifinals

Published in RSS 2022 Workshop on” Towards Robot Avatars: Perspectives on the ANA Avatar XPRIZE Competition, 2022

In this short paper, we discuss the main features of our semifinals entry to the ANA Avatar XPrize challenge in Miami, Florida, which placed 4th in the semifinals. A more detailed paper with our finals submission will follow soon.

Recommended citation: Marques, Joao MC, et al. "Commodity Telepresence with the AvaTRINA Nursebot in the ANA Avatar XPRIZE Semifinals." RSS 2022 Workshop on” Towards Robot Avatars: Perspectives on the ANA Avatar XPRIZE Competition. 2022. https://motion.cs.illinois.edu/papers/RSS2022Workshop-Marques-TelepresenceXPRIZE.pdf

Real-time Semantic 3D Reconstruction for High-Touch Surface Recognition for Robotic Disinfection

Published in IROS, 2022

This paper presentes a real-time semantic 3D reconstruction system for reconstructing and classifying environments in high-touch or low touch - and extends my previous disinfection planner to include this semantic information, showing that incorporating this information during planning improves disinfection performance by up to 20%

Recommended citation: Qiu, Ri-Zhao, Sun Yixiao, Correia Marques, Joao Marcos, Hauser, Kris. (2022). "Real-time Semantic 3D Reconstruction for High-Touch Surface Recognition for Robotic Disinfection" IROS 2022. https://ieeexplore.ieee.org/abstract/document/9981300

Pan-Tilt-Roll Televisualization with Adjustable Baseline Stereo

Published in 2^nd Workshop Toward Robot Avatars, IEEE International Conference on Robotics and Automation (ICRA), 2023

Depth perception plays an important role in teleoperated task completion. Most previous works on teleoperated depth perception with Head Mounted Displays had focused their attention on matching the user’s Intra-Pupillary Distance (IPD) on the HMD’s displays, but used fixed stereo cameras on the robot side to capture the environment. In this workahop paper, we developed a custom adjustable baseline stereo rig for use in teleoperated robotics and show, through a small user study (n=16), that matching the robot’s stereo baseline with the user’s IPD has a small, but significant effect in task completion time for depth-critical operations. This suggests that future Avatar design could benefit from robot-side IPD adjustment devices, especially for fine manipulation tasks. We also observed that scaling the number of Degrees of Freedom on an avatar’s neck showed diminishing returns after 2 DoFs, hinting that commercial pan-tilt units might be sufficient for most avatar applications, though more research is needed with a more diverse task set.

Recommended citation: Naughton, P., Nam, J. S., Marques, J. M. C., Peng, J.C., Zhu, Y., Kong, Q., Hauser, K. (2023). "Pan-Tilt-Roll Televisualization with Adjustable Baseline Stereo". In 2nd Workshop Toward Robot Avatars, IEEE International Conference on Robotics and Automation ICRA https://www.ais.uni-bonn.de/ICRA2023AvatarWS/contributions/ICRA_2023_Avatar_WS_Naughton.pdf

Commodity Telepresence with Team AVATRINA’s Nursebot in the ANA Avatar XPRIZE Finals

Published in 2^nd Workshop Toward Robot Avatars, IEEE International Conference on Robotics and Automation (ICRA), 2023

This workshop paper presents the techniques and technologies we employed in our successful entry on the ANA Avatar XPrize finals, in 2022 in Los Angeles. Our team, AvaTRINA, placed 4^th overall, being the only team to complete the full obstacle course without the use of any bulky Load Force Feedback devices on the operator`s arms. We believe augmented reality and assistive teleoperation modes are one viable path towards scalable and equitable adoption of avatar technologies.

Recommended citation: Marques, J.M.C., Peng, J.C., Naughton, P., Zhu, Y., Nam, J. S., Hauser, K. (2023) "Commodity Telepresence with Team AVATRINA’s Nursebot in the ANA Avatar XPRIZE Finals". In 2nd Workshop Toward Robot Avatars, IEEE International Conference on Robotics and Automation ICRA https://www.ais.uni-bonn.de/ICRA2023AvatarWS/contributions/ICRA_2023_Avatar_WS_Marques.pdf

Immersive Commodity Telepresence with the AVATRINA Robot Avatar

Published in International Journal of Social Robotics, 2024

Immersive robotic avatars have the potential to aid and replace humans in a variety of applications such as telemedicine and search-and-rescue operations, reducing the need for travel and the risk to people working in dangerous environments. Many challenges, such as kinematic differences between people and robots, reduced perceptual feedback, and communication latency, currently limit how well robot avatars can achieve full immersion. This paper presents AVATRINA, a teleoperated robot designed to address some of these concerns and maximize the operator’s capabilities while using a commodity light-weight human–machine interface. Team AVATRINA took 4th place at the recent $10 million ANA Avatar XPRIZE competition, which required contestants to design avatar systems that could be controlled by novice operators to complete various manipulation, navigation, and social interaction tasks. This paper details the components of AVATRINA and the design process that contributed to our success at the competition. We highlight a novel study on one of these components, namely the effects of baseline-interpupillary distance matching and head mobility for immersive stereo vision and hand-eye coordination.

Recommended citation: Marques, J.M.C.*, Naughton, P.*, Peng, J.-C.*, Zhu, Y.*, Nam, J. S., Kong, Q., Zhang, X., Penmetcha, A., Ji, R., Fu, N., Ravibaskar, V., Yan, R., Malhotra, N., and Hauser, K., (2024). "Immersive Commodity Telepresence with the TRINA Robot Avatar ". International Journal of Social Robotics https://link.springer.com/article/10.1007/s12369-023-01090-1

On the Overconfidence Problem in Semantic 3D Mapping

Published in International Conference on Robotics and Automation (ICRA) 2024, 2024

Semantic 3D mapping, the process of fusing depth and image segmentation information between multiple views to build 3D maps annotated with object classes in real-time, is a recent topic of interest. This paper highlights the fusion overconfidence problem, in which conventional mapping methods assign high confidence to the entire map even when they are incorrect, leading to miscalibrated outputs. Several methods to improve uncertainty calibration at different stages in the fusion pipeline are presented and compared on the ScanNet dataset. We show that the most widely used Bayesian fusion strategy is among the worst calibrated, and propose a learned pipeline that combines fusion and calibration, GLFS, which achieves simultaneously higher accuracy and 3D map calibration while retaining real-time capability and adding only 525 learned parameters to the pipeline. We further illustrate the importance of map calibration on a downstream task by showing that incorporating proper semantic fusion to an indoor object search agent improves its success rates.

Recommended citation: Marques, J.M.C., Zhai, A., Wang, S. and Hauser, K., (2024). On the Overconfidence Problem in Semantic 3D Mapping”, 2024 IEEE International Conference on Robotics and Automation (ICRA) https://arxiv.org/abs/2311.10018

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015