Robotic Manipulation | Electrical Engineering and Computer Science
Introduces the fundamental algorithmic approaches for creating robot systems that can autonomously manipulate physical objects in unstructured environments such as homes and restaurants. Topics include perception (including approaches based on deep learning and approaches based on 3D geometry), plan

Before you start
- Basic Python familiarity
- Comfort with algebra or calculus basics
- Interest in robotics systems
About this guide
Introduces the fundamental algorithmic approaches for creating robot systems that can autonomously manipulate physical objects in unstructured environments such as homes and restaurants. Topics include perception (including approaches based on deep learning and approaches based on 3D geometry), planning (robot kinematics and trajectory generation, collision-free motion planning, task-and-motion planning, and planning under uncertainty), as well as dynamics and control (both model-based and learning-based).
Homework assignments will guide students through building a software stack that will enable a robotic arm to autonomously manipulation objects in cluttered scenes (like a kitchen). A final project will allow students to dig deeper into a specific aspect of their choosing. The class has hardware available for ambitious final projects, but will also make heavy use of simulation using cloud resources.
Common questions
What will I learn in Robotic Manipulation | Electrical Engineering and Computer Science?
Introduces the fundamental algorithmic approaches for creating robot systems that can autonomously manipulate physical objects in unstructured environments such as homes and restaurants. Topics include perception (including approaches based on deep learning and approaches based o
Is Robotic Manipulation | Electrical Engineering and Computer Science free?
HumanoidHub has source-backed evidence that this guide is free to access through MIT OpenCourseWare. Check the provider page for certificate or upgrade terms.
Do I need any prerequisites?
Recommended prep: Basic Python familiarity; Comfort with algebra or calculus basics; Interest in robotics systems.
How long does it take?
1 hours total. Most learners complete this guide in self-directed sessions over a few weeks.
Does it offer a certificate?
This guide does not include a formal certificate. Focus is on the learning material itself.
Related guides

A faster way to teach a robot
A new technique enables a human to efficiently fine-tune a robot that failed to complete a desired task with very little effort on the part of the human. Their system uses algorithms, counterfactual explanations, and feedback from the user to generate synthetic data it uses to quickly fine-tune the

Teaching Humanoid Robots Real-World Skills at MIT CSAIL’s Living Lab
Member Resources MIT In This Section Home MIT In This Section Filter Options In This Section Filter Options In This Section # Teaching Humanoid Robots Real-World Skills at MIT CSAIL’s Living Lab At MIT CSAIL's Living Lab, humanoid robots are learning to adapt, manipulate, and solve real p

Unit 8. Robotics | Brains, Minds and Machines Summer Course | Brain and Cognitive Sciences
This page summarizes the unit topic and activities, and links to lecture videos, notes and further study resources.
[PDF] 1st Reading - Personal Robots Group
5.6. Learning results The tutoring of tasks exemplifies our approach to teaching as a collaborative interac-tion. Joint attention is established both on the object level and on the task structure level. The robot uses subtle expression to indicate to the human tutor when it is ready to learn somethin
[PDF] Children, Humanoid Robots and Caregivers - MIT CSAIL
Conclusions This paper described a framework for developmental object perception and learning on a humanoid robot, which aims at teaching humanoids as children. We described algorithms to learn about the robot’s self appearance and its surrounding world. The epige-netic principle established the fou
[PDF] Foundations for a Theory of Mind for a Humanoid Robot - Research
• Chapter 8 : Detecting Faces and Head Pose One final primitive perceptual process will be required. The robot will need to find human faces in the visual scene and to extract the orientation of the head as a measurement of where that person is attending. This orientation direction will be used later
Robots that use these skills

myBuddy
Elephant Robotics
myBuddy is Elephant Robotics’ dual-arm, semi-humanoid desktop robot launched in 2022 for research and education.

Sanbot Elf
Qihan Technology
Sanbot Elf is a compact wheeled service robot from Qihan Technology for reception, guidance, and interactive engagement.

Sanbot Nano
Qihan Technology
Sanbot Nano is a compact wheeled companion/service robot from Qihan, built for voice interaction and basic autonomous navigation.
Refer a learner and get early access to our paid pathways and 1:1 mentorship pilot.
Join referral listNew robots, industry moves, and funding in your weekly robotics briefing.
Unsubscribe anytime.