Shohei Fujii
Robotics Software Research Engineer at DENSO
Toyota, Japan
Summary
👤
Senior🎓
Top SchoolShohei Fujii is a Robotics Software Research Engineer with 13 years of experience building real-world automation systems, from SLAM-based mobile robots and low-cost self-driving factory vehicles to advanced bin-picking vision and automated calibration systems. He blends embedded and full-stack development with robotics research, shipping production-ready ROS stacks, MPC motion controllers, multi-robot dispatching, and Docker/Kubernetes deployment for factory fleets. At DENSO and MUJIN he led end-to-end projects integrating perception, planning, and high-speed middleware (ZeroMQ/REST), and his open-source work includes meaningful contributions to Darknet_ROS and extending OpenRAVE’s planning and visualization capabilities. Comfortable moving between low-level C++/ROS and higher-level web UIs and services, he also brings academic rigor from The University of Tokyo and ongoing PhD work at Nanyang Technological University. Notably, he designs systems with automated recovery and calibration in mind—aiming to eliminate tedious manual tuning in continuous industrial operation.
13 years of coding experience
2 years of employment as a software developer
University of TokyoDoctor of Philosophy - PhD, Mechanical and Aerospace Engineering, Doctor of Philosophy - PhD, Mechanical and Aerospace Engineering at Nanyang Technological University Singapore
Stackoverflow
1reputation
0reached
1answer
0questions
Github Skills (15)
object-detection10
computer-vision10
c-language10
robotics10
cprogramming-language10
python10
ros10
openra10
deeplearning-ai9
deep-learning9
boost8
type-conversion6
ios6
realm6
swift6
Programming languages (17)
Github contributions (5)
rdiankov/openrave
Apr 2014 - Sep 2021
Open Robotics Automation Virtual Environment: An environment for testing, developing, and deploying robotics motion planning algorithms.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:1 review, 22 commits, 4 PRs in 7 years 6 months
Contributions summary:Shohei primarily focused on modifying and extending the OpenRAVE library, a robotics simulation environment. Their contributions include fixing bugs related to argument matching and potential segmentation faults, as well as refactoring code to improve performance. They also implemented new features, specifically for RRT planner dumping and adding an array of boxes in the viewer. The user made several code changes to Python bindings and created the drawing of box arrays feature.
deployingroboticsvirtual-environmentdevelopingtesting
leggedrobotics/darknet_ros
Oct 2017 - Oct 2017
YOLO ROS: Real-Time Object Detection for ROS
Role in this project:ML Engineer
ML EngineerContributions:5 commits, 1 PR, 3 comments in 14 days
Contributions summary:Shohei primarily contributed to the `darknet_ros` repository by modifying the object detection implementation. They added and removed functionality related to bounding box message types, which included changes to the `YoloObjectDetector` class and header file. The user's commits demonstrate work on publishers and message handling, likely for integrating with ROS. They also removed unused components and readded a result member variable, suggesting an iterative development approach focused on object detection and ROS integration.
human-detectiondeep-learningcomputer-visionobject-detectionreal-time-object-detection
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.