Pablo Palafox
About
Detail
Co-Founder & CEO
San Francisco, California, United States
Résumé
Jobs
verified_user
0% verified
Co-Founder & CEOHappyRobotNov 2023 - Current (2 years 8 months)Transforming enterprises with AI workers- HCo-FounderHappyrobot YC SNov 2023 - Current (2 years 8 months)Building AI assistants for logistics.
- Research InternPRO UnlimitedOct 2021 - Jan 2022 (4 months)
- Research InternMetaMay 2021 - Sep 2021 (5 months)Working at Facebook Reality Labs (FRL)
- Researcher and PhD Candidate @ 3D AI Lab under Prof. Angela DaiTechnical University of MunichDec 2019 - Mar 2022 (2 years 4 months)Supervisor: Prof. Angela Dai Have a look at my projects -> https://pablopalafox.github.io
- Research Assistant @ Daniel Cremers' Computer Vision GroupTechnical University MunichFeb 2019 - Jan 2020 (1 year)Topic: Local Tracking and Mapping for Direct Visual SLAM Advisor: Nikolaus Demmel - Supervisor: Prof. Daniel Cremers
- Research Assistant @ Matthias Niessner's Visual Computing & Artificial Intelligence GroupTechnical University MunichOct 2018 - May 2019 (8 months)Topic: Sceneflow prediction in Pointclouds and Voxelgrids using Deep Learning Advisor: Prof. Matthias Niessner
- Software Engineer [Sidejob]IPB SystemsOct 2016 - Jul 2017 (10 months)Development of wifi- and sound-based anti-drone systems using Deep Learning.
- Undergraduate Student Researcher [Research Grant]Universidad Politécnica de MadridNov 2015 - Jun 2016 (8 months)http://blogs.upm.es/robcib/2016/09/21/landing-on-ugv/ During this research grant, awarded by the Spanish Ministry of Education, I worked at the Centre for Automation and Robotics (UPM-CSIC) of the Technical University of Madrid developing an Autonomous Landing system for an Unmanned Aerial Vehicle. More precisely, we implemented an algorithm that allowed a drone to autonomously take-off from a moving platform, get to a certain height, detect and follow the moving platform autonomously and, when told to (by pressing a button in a controller), land on the platform while the latter was still in motion. This project idea was motivated by the Mohamed Bin Zayed International Robotics Challenge.
- Computer Vision EngineerRobdos Team Underwater RoboticsSep 2014 - Sep 2017 (3 years 1 month)Robdos Team is a multidisciplinary student association from the Technical University of Madrid developing an Autonomous Underwater Vehicle. We participated in euRathlon 2015 and 2017. I was in charge of detecting buoys and mannequins underwater. I implemented both a C++ algorithm based on traditional Computer Vision for detecting the former and a trained cascade person-classifier for detecting the mannequins. We used ROS as a framework for our robot system.
Education
verified_user
0% verified
- PProfessional Degree in Music, PianoProfessional Music Conservatory Sebastián Durón
- Master of Science - MS, Robotics and ElectronicsUniversidad Politécnica de MadridDouble Degree with Technical University of Munich
- ThePowerMBA Future Leaders Program, Business Administration and Management, GeneralthePower
- Master's Thesis, Computer Vision GroupTechnical University of MunichTopic: Local Tracking and Mapping for Direct Visual SLAM Advisor: Nikolaus Demmel Supervisor: Prof. Daniel Cremers
- Master of Science - MS, Mechanical EngineeringTechnical University of MunichProjects: - "Analyzing SLAM: RGB-Only & RGB-D". Project for the course "3D Scanning and Motion Capture" at Visual Computing Group (headed by Prof. Matthias Niessner) - "Development and Implementation of a Deep Learning-based Computer Vision Pipeline for Lane Detection" (Semester Project at Chair of Automotive Technology )
- Bachelor of Science - BS, Robotics and ElectronicsUniversidad Politécnica de Madrid
- Doctor of Philosophy - PhD, Computer Vision & Deep LearningTechnical University of Munich
Awards
verified_user
0% verified
- Postgraduate Scholarship "Becas Postgrado Mutua Madrileña"MUTUA MADRILEÑAJul 2017Postgraduate Scholarship awarded to 40 Spanish students for studying a Masters abroad.
- JJumping TalentMar 2016Selected as one of the 96 most promising university students in Spain (out of more than 5.000 candidates) to take part in an event sponsored by 12 top multinational companies.
- Excellence ScholarshipComunidad de MadridMar 2013Scholarship awarded for an excellent GPA
Publications
verified_user
0% verified
- SSemanticDepth: Fusing Semantic Segmentation and Monocular Depth Estimation for Enabling Autonomous Driving in Roads withSensors MPDIJul 2019Typically, lane departure warning systems rely on lane lines being present on the road. However, in many scenarios, e.g., secondary roads or some streets in cities, lane lines are either not present or not sufficiently well signaled. In this work, we present a vision-based method to locate a vehicle within the road when no lane lines are present using only RGB images as input. To this end, we propose to fuse together the outputs of a semantic segmentation and a monocular depth estimation architecture to reconstruct locally a semantic 3D point cloud of the viewed scene. We only retain points belonging to the road and, additionally, to any kind of fences or walls that might be present right at the sides of the road. We then compute the width
- ARobust Visual-Aided Autonomous Takeoff, Tracking, and Landing of a Small UAV on a Moving Landing Platform for Life-LongApplied Sciences MDPIJun 2019Robot cooperation is key in Search and Rescue (SaR) tasks. Frequently, these tasks take place in complex scenarios affected by different types of disasters, so an aerial viewpoint is useful for autonomous navigation or human tele-operation. In such cases, an Unmanned Aerial Vehicle (UAV) in cooperation with an Unmanned Ground Vehicle (UGV) can provide valuable insight into the area. To carry out its work successfully, such as multi-robot system requires the autonomous takeoff, tracking, and landing of the UAV on the moving UGV. Furthermore, it needs to be robust and capable of life-long operation. In this paper, we present an autonomous system that enables a UAV to take off autonomously from a moving landing platform, locate it using visual