TEK3980 – From Pixels to Motion: Perception and Control for Modern Robots

Knowledge:

After completing this course, you will be able to

• explain the operating principles, characteristics, and noise models of common robotic sensors and actuators
• describe sampling theory and signal processing fundamentals relevant to real-time perception
• summarize the camera pinhole model, calibration (intrinsic/extrinsic), and geometric vision
• outline Bayesian estimation, uncertainty propagation, and sensor fusion concepts
• compare motion planning methods and explain control strategies, including trade-offs in optimality and real-time feasibility
• identify systems integration challenges such as jitter, resource constraints, and fault handling

Skills:

After completing this course, you will be able to

• calibrate and characterize sensors to acquire synchronized datasets
• implement signal processing pipelines and evaluate performance using quantitative metrics
• build geometric vision modules for feature extraction and pose estimation
• implement and tune state estimators for pose and velocity
• engineer a real-time perception pipeline that handles buffering and failure modes
• integrate perception, planning, and control into a cohesive autonomy stack

General competence:

After completing this course, you will be able to

• critically assess trade-offs between accuracy, robustness, and hardware requirements (energy, memory, compute)
• practice responsible and ethical use of data, showing awareness of bias and limitations in dataset curation
• collaborate effectively in teams and communicate technical results through structured reports and presentations

Students who are admitted to study programmes at UiO must each semester register which courses and exams they wish to sign up for in Studentweb.

This course is open for admission to students on the bachelor's programme Technology Systems: Science and Engineering. Please refer to the programme description for admission requirements.

The course uses a blend of lectures, weekly laboratory work, and a major team project.

• Laboratories: Practical sessions include camera characterization, visual odometry with turtle bots in a motion-capture setup, and implementing planning/control algorithms.
• Project work: This is a 4-week intensive project where students develop an end-to-end control system for a robot, integrating perception and planning.

Mandatory activities:

• weekly concept checks: online quizzes to monitor progress
• lab check-offs: feedback provided by group teachers throughout the semester
• peer reviews: groups will review each other's work during the project period to develop feedback skills

The final grade is based on a combination of assessments:

• 30% group portfolio: final project report
• 20% presentation: group or individual presentation of the final project
• 50% individual oral exam: reflections on the project and answering questions on a case study involving an end-to-end autonomy stack

Students who can document a valid reason for absence from the regular examination are offered a postponed examination at the beginning of the next semester.

Re-scheduled examinations are not offered to students who withdraw during, or did not pass, the original examination.