Surya Balaji

Developing perception-driven ROS 2 motion planning pipeline for 7-DOF Kinova mobile manipulator in Isaac Sim, integrating cuRobo with spherically abstracted 3D LiDAR point cloud for GPU-accelerated collision avoidance

Evaluate lab competency across 3 lab sections covering GPIO, FSM design, interrupts, and SPI/ADC/UART drivers

Engineered EMG signal acquisition pipeline utilizing hardware bandpass filtering, rectification, and enveloping to isolate muscle activity via voltage thresholding on Arduino Uno R4

A custom autonomous differential-drive racecar that won 1st place against 12 teams. The system runs on a preemptive RTOS kernel built from scratch and navigates the track using multi-rate sensor fusion of LiDAR, IR, and IMU data.

An EMG-controlled prosthetic arm that classifies hand gestures in real time using TinyML models deployed on an ESP32. The full pipeline spans signal acquisition, dataset labeling, model training, and on-device inference, driving a custom 7-DOF 3D-printed arm.

A fully bare-metal real-time game console, hardware and software, built with Elijah Silguero. We designed the custom PCB and enclosure, then wrote a 3D game engine that renders at 20 FPS using interrupts and SPI, all within the tight constraints of 128 KB flash and 32 KB RAM.

A surface-EMG human-system interface that lets a user drive interactions inside a VR environment through muscle activation instead of a controller. Flexing a monitored muscle group produces a trigger that the VR scene reacts to in real time.

A surface-EMG interface that turns muscle activation into drive commands for a wheeled rover, letting a user steer the platform hands-free.

A surface-EMG readout that measures how hard a muscle is contracting and displays the strength in real time, serving as an early building block for the team's later EMG-driven control projects.