About
I study Robotics and Computer & Information Science at the University of Pennsylvania. My work spans autonomous driving truck failure analysis, Machine Learning based f1tenth car control using event cameras, mobile robot design and wall following implementation, LiDAR and GPS-based pedestrian and cyclist detection with sensor fusion, and real-time collision prediction systems.
Education
University of Pennsylvania
Master of Science in Engineering, Robotics and Computer Science
Concentration: Computer Vision
Expected May 2027 · GPA: 3.81/4.0
University of Tokyo
Bachelor of Engineering, Mechanical Engineering
March 2023 · GPA: 3.64/4.0
Featured Projects
Mobile Robots Competition
Designed and fabricated a mobile robot using CAD, laser cutting, and 3D printing. Wrote embedded C code for motor control, ToF wall-following, and a wireless web interface using UDP and IP.
Result: Awarded 2nd place in the final competition.
Event Camera Driving Simulation
Implemented driving simulators for visualizing event-camera data on an F1TENTH car using Gazebo, CARLA, and ROS. Collected datasets and trained a vision transformer model to compute motion control from event images.
Impact: Improved data generation efficiency by reducing redundancy and cutting time by 70%.
F1TENTH Autonomous Racing Cars
Developed a 1/10-scale autonomous racing car by designing and implementing perception, motion planning, localization, and vehicle control algorithms using Python, C++, ROS2, and SLAM. Integrated the complete autonomous driving pipeline and optimized racing performance on a competitive track.
Impact: Achieved second place for the fastest lap in the final autonomous racing competition.
Traffic Collision Prediction System
Designed and built a real-time collision prediction system among pedestrians, cyclists, and an intelligent wheelchair. Implemented C++ ROS code for LiDAR-based detection and used Extended Kalman Filter sensor fusion for position estimation.
Automatic Braking System for Wheelchair
Developed an automatic emergency braking system for an intelligent wheelchair by integrating AI camera-based object detection with ROS to identify obstacles and trigger braking in real time. Implemented the control logic in Python to improve navigation safety in dynamic environments.
Focus: Integrated perception and braking control for real-time collision avoidance.
Experience
Vijay Kumar Lab · Research Assistant
May 2026 – Present- Design and build VLA control system of drones with robotic arms to complete tasks like turning valves with NVIDIA IsaacSim.
ISUZU · Advanced Engineering - AI & Autonomous Driving Intern
May 2026 – August 2026- Investigated autonomous truck on-road test failures by tracing issues across a large-scale perception, planning, and control software architecture built with Bazel and protobuf, identifying root causes through code analysis and debugging.
- Used SQL to analyze autonomous driving on-road test data and quantitatively evaluate performance on dashboards.
Vijay Kumar Lab · Research Intern
May 2025 – May 2026- Implemented event-camera driving simulators using Gazebo, CARLA, and ROS.
- Trained vision transformer models for motion control from event-camera images.
BOSCH · Software Intern
August 2023 – September 2023- Built MATLAB-based maps for autonomous driving and ADAS signal visualization.
- Improved CAN signal processing by fixing decoding issues and refining output accuracy.
Skills
Publications
Hori, K., Watanabe, K., Tanaka, T., Nishi, M., & Ito, T. (2026). Visibility Evaluation Around Unsignalized Intersections with Occlusion From Arbitrary On-road Viewpoints Using Point Cloud Maps.
Watanabe, K., Nishi, M., & Ito, T. (2025). Placement design of various roadside sensors for stochastic position prediction of traffic participants on community roads.
Contact
Email: mari3511n@gmail.com
LinkedIn: linkedin.com/in/marika-nishi
GitHub: github.com/marika340