RAIN
LMS login Apply
Cover of RDA 212 AI for Humanoid Robotics

RDA 212

AI for Humanoid Robotics

Perception, Learning, Language and Embodied Intelligence

Humanoid robots have left the research laboratory. Machines with two arms, two legs and a head now walk warehouse floors, carry totes, greet visitors and answer questions, and the same advances in learning, perception and language that make them possible also power service robots of every shape: delivery robots, hospital assistants, receptionists and tutors. Building such a robot draws on nearly everything a robotics engineer knows, from motors and kinematics to neural networks and large language models, and it raises questions of safety, trust and ethics that a factory arm never did. This book teaches the methods of artificial intelligence that give humanoid and service robots their abilities, and how to integrate them into a robot that works with people.

13 chapters in 5 parts, 251 pages. Editor-in-Chief: Olusola Sayeed Ayoola. Published by RAIN, Ibadan, 2026.

Order a copy Read it (owners and RAIN trainees) Certification

Contents

Open a chapter to see its sections. Each chapter ends with a QR code for its free assessment.

1Humanoid and Service Robots
  • 1.1 History and current platforms
  • 1.2 Anatomy of a humanoid: degrees of freedom, actuators and sensors
  • 1.3 The sense-think-act loop and robot software stacks
  • 1.4 Case study: sizing a humanoid's knee

Take the Chapter 1 assessment

2Neural Networks for Robotics
  • 2.1 Neurons, layers and backpropagation
  • 2.2 Training on a GPU and on the edge
  • 2.3 Deploying models on Raspberry Pi and Jetson
  • 2.4 Explainable AI for robot networks
  • 2.5 Case study: learning a robot arm's inverse kinematics

Take the Chapter 2 assessment

3Computer Vision for Robots
  • 3.1 Camera models and calibration
  • 3.2 Object detection and tracking
  • 3.3 Pose estimation of people
  • 3.4 Depth sensing and stereo vision
  • 3.5 Obstacle detection and road awareness
  • 3.6 Case study: calibrating, detecting and measuring depth

Take the Chapter 3 assessment

4Generative Models and Vision Algorithms
  • 4.1 GANs and their use for synthetic training data
  • 4.2 Image segmentation for manipulation
  • 4.3 Sim-to-real transfer
  • 4.4 Case study: a GAN, a grasp from a mask, and randomised training

Take the Chapter 4 assessment

5Multisensor Perception
  • 5.1 Fusing vision, depth and IMU data
  • 5.2 Tactile and force sensing
  • 5.3 Case study: estimating tilt, tracking with a late camera, and feeling contact

Take the Chapter 5 assessment

6Humanoid Kinematics
  • 6.1 Kinematic chains for arms, legs and heads
  • 6.2 Whole-body forward and inverse kinematics
  • 6.3 Workspace analysis
  • 6.4 Case study: a humanoid's upper body reaches and looks

Take the Chapter 6 assessment

7Balance and Locomotion
  • 7.1 Centre of mass and support polygon
  • 7.2 Zero moment point
  • 7.3 Gait generation
  • 7.4 Learning-based locomotion
  • 7.5 Case study: standing, walking and recovering from a push

Take the Chapter 7 assessment

8Grasping and Manipulation
  • 8.1 Grasp types and grasp quality
  • 8.2 Vision-guided pick-and-place
  • 8.3 Learning from demonstration
  • 8.4 Case study: choosing a grasp, calibrating the camera, and learning to reach

Take the Chapter 8 assessment

9Speech and Natural Language for Robots
  • 9.1 Speech recognition and speech synthesis
  • 9.2 Intent recognition and dialogue management
  • 9.3 Multilingual interaction in Nigerian languages
  • 9.4 Case study: a multilingual receptionist listens and understands

Take the Chapter 9 assessment

10Large Language Models as Robot Brains
  • 10.1 LLM planning and task decomposition
  • 10.2 Vision-language models
  • 10.3 Grounding language in actions; tool calling into ROS 2
  • 10.4 Safety limits for LLM-controlled robots
  • 10.5 Case study: attention, grounded planning and a safety shield

Take the Chapter 10 assessment

11Human-Robot Interaction
  • 11.1 Social cues, gaze and gesture
  • 11.2 Trust, transparency and user studies
  • 11.3 Collaborative-robot safety (ISO 10218, ISO/TS 15066)
  • 11.4 Case study: approaching people safely and measuring trust

Take the Chapter 11 assessment

12Reinforcement Learning for Robots
  • 12.1 Policy-gradient methods
  • 12.2 Simulation environments (Isaac Sim, MuJoCo, Gazebo)
  • 12.3 Reward design and safety
  • 12.4 Case study: learning a reaching controller, stable simulation and safe rewards

Take the Chapter 12 assessment

13Integrating a Humanoid System
  • 13.1 System architecture and ROS 2 integration
  • 13.2 Testing and validation
  • 13.3 Ethics of humanoid robots
  • 13.4 Capstone: a receptionist robot
  • 13.5 Case study: budgeting, reliability and testing for the receptionist

Take the Chapter 13 assessment

Order a copy

Printed copies are delivered anywhere in Nigeria or collected at RAIN in Ibadan; digital copies arrive by e-mail with your book owner code. We will reply with the price, delivery cost and payment details.

Schools and companies ordering several copies: put the number you need and we will quote.

Other RAIN textbooks

AIML 101 Building and Deploying AI ApplicationsAIML 111 Data Science with PythonAIML 112 Machine Learning IAIML 211 Machine Learning IIAIML 212 Deep LearningRDA 111 Product Design and Development

All the books