Skip to content
Tenzok
Home
Services
Student Projects
BlogAboutContact
All student projects

4 scoped briefs

2 mini · 2 major

Robotics, Drones & Autonomous Systems

Autonomy is the layer above the chassis — kinematics, control, state estimation, perception — and two failures dominate: hardware built before a behaviour is proven in simulation, and a TF tree that is silently wrong, so the robot can never localise no matter how good the LiDAR is. We build in Gazebo first, move to hardware second, and keep the logs.

ROS 2 JazzyGazebo SimNav2SLAM ToolboxURDF / TF2PX4 SITL + PixhawkMAVSDK / MAVLinkNVIDIA JetsonOpenCV / RT-DETR
Start a projectDiscuss a custom brief

The standard

Build the system. Understand every trade-off.

Every brief ends with working software, documented decisions, and evidence you can present—not a folder of code you cannot explain.

Two audiences, one engineering standard

Academic depth meets production discipline.

For students

Pick a brief below, or bring the problem statement your department handed you. We architect it with you, review every commit, deploy it to a real URL, and rehearse the viva until no question surprises you.

See student support

For companies

ROS 2 integration and Nav2 tuning, manipulator kinematics, PX4/MAVLink mission and ground-station software, simulation rigs that regression-test autonomy before it meets a real floor, and edge perception on Jetson-class hardware using a permissively licensed detector (RT-DETR) where Ultralytics YOLO's AGPL-3.0 terms do not fit a commercial build.

Discuss a company build

Mini projects

Focused scope. Real engineering.

Three to four weeks. Narrow enough to finish, deep enough that you learn the decision that actually matters.

2 briefs
Mini project3–4 weeks

PID Line-Follower: A Tuning Study

A differential-drive bot that holds a line at speed under a tuned PID loop, with step-response and cross-track-error plots that prove the gains instead of the bang-bang wobble most builds settle for.

ESP32C++IR reflectance arrayPID controlPython (log analysis)

You walk away with

  • Differential-drive kinematics in code, not hand-guessed PWM
  • Step-response and cross-track-error plots for three gain sets, from logged CSVs
  • Bang-bang baseline benchmarked on the same track
  • Anti-windup and filtered derivative, each with the failure it fixes on video
  • Stretch goal, only once the tuning study lands: wall-following maze solve
Mini project3–4 weeks

4-DOF Arm: Forward and Inverse Kinematics in Simulation

A simulated arm that reaches a commanded (x, y, z) using an inverse-kinematics solver you derived yourself — validated against your own forward model across the whole workspace, not the three poses that happen to work.

ROS 2 JazzyGazebo SimURDFTF2PythonNumPy

You walk away with

  • URDF with documented DH parameters, loading in Gazebo and RViz
  • Forward-kinematics function validated against the TF poses RViz reports
  • Analytical IK solver with reachability and singularity rejection
  • FK(IK(pose)) error map over a sampled workspace grid, plotted
  • Joint-trajectory pick-and-place in Gazebo, driven by your own solver

Major projects

Capstones you can defend.

Ten to twelve weeks. Architecture, trade-offs, failure modes, deployment, and evidence—the project that carries an interview.

2 briefs
Major project10–12 weeks

Autonomous Indoor Rover (SLAM + Nav2)

A rover that maps an unseen floor, then runs a waypoint mission through it while avoiding people who step into its path — with rosbags, a defensible TF tree, and map artefacts that survive a viva.

ROS 2 JazzyNav2SLAM Toolboxrobot_localization (EKF)RPLIDAR + IMUJetson Orin Nano

You walk away with

  • Gazebo world matching the real floor plan, every behaviour proven there first
  • TF tree (map → odom → base_link → sensors) printed and defended, because it fails silently
  • EKF fusing wheel odometry and IMU, drift measured against ground truth before and after
  • SLAM Toolbox map (.pgm + .yaml) with loop closure demonstrated
  • Nav2 mission over five waypoints with dynamic obstacle avoidance, rosbags for every run including the failures
Major project12–14 weeks

Survey Drone with Onboard Detection and Geotagged Reporting

A ready-to-fly quadcopter that runs a planned survey grid, detects and geotags targets onboard, and lands with a report — flown and broken in PX4 SITL long before the props ever spin.

PX4 SITL + Pixhawk (ready-to-fly airframe)Gazebo SimMAVSDK / MAVLinkQGroundControlJetson Orin NanoRT-DETR

You walk away with

  • Full mission in PX4 SITL + Gazebo, with injected GPS loss, RC loss and low battery, and the failsafe response to each
  • Detector fine-tuned on a public aerial dataset, mAP reported on a held-out set of your own labelled frames
  • Onboard inference on the companion computer at a measured FPS, with PX4 .ulg logs reviewed per flight
  • Geotagged detections fused with MAVLink position and attitude, exported as GeoJSON and mapped
  • Flight authorisation on file before any outdoor flight: Drone Rules 2021 Rule 22 R&D exemption via the institution, green-zone airspace inside institution-controlled premises, ≤400 ft AGL, VLOS, named faculty supervisor, DigitalSky airspace-map check, stated all-up weight and category, no flight over people — otherwise SITL plus a netted indoor cage and no outdoor flight at all

Explore more

Other engineering domains

Search every brief
Python Full-StackJava & EnterpriseAI & LLM ApplicationsMachine LearningDeep LearningData EngineeringMobile AppsCloud & DevOpsCybersecurityIoT & EmbeddedJavaScript Full-StackVLSI & Chip DesignPower Electronics, EV & Energy SystemsSignal Processing & Wireless CommunicationsData Analytics & Business IntelligenceTest Automation & SDETComputer Networks & Protocol Simulation
Your next build starts here

Turn the idea into software people trust.

Bring us a product brief, a business problem, or a final-year project. We’ll turn it into a clear scope, a working build, and a handover you fully own.

Start Your ProjectSend your brief

Prefer email? info@tenzok.in

Tenzok

A product engineering studio for ambitious companies, founders, and students who want real, production-minded work.

info@tenzok.in

Company

HomeBlogAboutContactFAQ

Services

MentorshipStudent ProjectsCompany ServicesDigital MarketingLaunch Support

Project domains

Python Full-StackJava & EnterpriseAI & LLM ApplicationsMachine LearningExplore all 18 domainsRSS feed

© 2026 Tenzok. All rights reserved.

Obsession · Purpose · Excellence