Programming A Driverless Car Chapter 9: Introduction to Robotics

Introduction to Robotics

What is a robot?
A robot is an active artificial agent whose environment is the physical world. We may also say a programmable, multifunction manipulator designed to move material, parts, tools or specific devices through variable programmed motions for the performance of a variety of tasks.
There are many types of robots:

  • Robot Manipulators
  • Stationary Robots
  • Industrial Robots
  • Educational Robots
  • Mobile Robots

Robot Manipulators are used to handle the object, pick/place the object or material handling industries.
Mobile robots can be moved from one place to another. Used mainly for surveillance, security purposes, mining robots, finding objects, domestic tasks. They can be used using legged locomotion or wheeled locomotion. One of the great example is: In 1979, a nuclear accident in the USA caused a leak of radioactive material which led to production of special robots which can handle the radioactive materials.
We also have: Walking Robots which use legs for motion or Humanoid Robots which are formed like a human structure.
There are Industrial robots which can be used for:

  • Inspection of quality testing
  • Materials handling
  • Welding
  • Improving productivity- Qualitative production
  • Laboratory Applications

Educational Robots can be extensively used in Education. Eg. Robolab, Lego and RoboCup Soccer.

Domestic Robots are of 2 types which are designed to perform household tasks and modern toys which are programmed to do things like talking, walking and dancing etc.
Tasks performed by Robots and Autonomous Robots:
Robots are used by humans for various tasks:

  1. Dirty Tasks: These are the tasks which are not liked by humans to perform like drainage cleaning, underwater pipe cleaning and etc.
  2. Repetitive Tasks: Some of the repetitive tasks that are performed in an industry like capping products, picking up, putting down, packing the products. This is for mass production.
  3. Dangerous Tasks: Some of the tasks which are not considered suitable for humans like working in a mine industry, lime industry or where the temperature is too different for human bodies.
  4. Impossible Tasks: Tasks that are considered impossible for humans can also be performed by robots. Like lifting up heavy weights, roaming on Mars or any planets, or diagonalizing inside human body.
  5. Robots assisting the handicapped
  6. Can operate Humans at a much higher precision value than humans
  7. Cheaper on a long term basis.

Autonomous Robots:
Autonomous robots are intelligent machines capable of performing tasks in the world by themselves, without explicit human control. Example ranges from autonomous helicopters to Roomba, the robotic vacuum cleaner.
The control of autonomous robots involves a number of subtasks:
-Understanding and modeling of the mechanism: Kinematics, Dynamics and Odometry
-Reliable control of the actuators: Closed loop controls can help to minimize error and make more precise output.
-Generation of task-specific motions- Path planning
-Integration of Sensors- Selection and interfacing of various types of sensors
-Coping with noise and uncertainty- Filtering of sensor noise and actuator uncertainty.
-Creation of flexible control policies- Control has to deal with new situations
Problems with traditional industrial robots
Traditional industrial robot control uses robot arms and largely precomputed motions:

  • Programming using “tech box”
  • Repetitive Tasks
  • High Speed
  • Few sensing operations
  • High precision movements
  • Pre-planned trajectories and task policies
  • No interaction with humans

Problems that we face with traditional programming techniques is that the industrial robots lack key capabilities necessary in intelligent environments. They have limited online sensing, no incorporation of uncertainty, no interaction with humans, reliance on perfect task information, complete reprogramming for new tasks.
Requirement of Robots in Intelligent Environments:
Autonomy
-Robots have to be capable of achieving task objectives without human input
-Robots have to be able to make and execute their own decisions based on sensor information
Intuitive Human-Robot Interface
-Use of robots in smart homes do not require extensive user training
-Commands to robots should be natural for inhabitants
Adaptation
-Robots have to be able to adjust to changes in the environment
Autonomous Vehicles:
Vehicles that can move from one point to another without any human interaction with the help of special algorithms are called autonomous vehicles. They implement various number of well placed sensors that detect different things such as other vehicles, people, traffic lights and movement of other vehicles.
The technology of the Self Driving Cars includes:

  • Anti-Lock Brakes
  • Electronic Stability Control
  • Adaptive Cruise Control
  • Lane-Departure Warning
  • Self Parking
  • Automated guided vehicle systems
  • Lidar-systems or Cruise automated Systems
  • Infrared cameras

LIDAR is a ranging system comprising of 64 lasers to analyze the environment in a proper way. RADAR that can detect a car’s blind spot and help to alert.
Stereo Vision for reading the road ahead, spotting traffic hazards and watching  for pedestrians.
The LIDAR System has:
-Vertical and horizontal setup of the system possible
-Image acquisition with fully integrated NIKON DSLR camera
-3D model of the VZ scanner with continuous rotation of the scanning head for highly efficient mobile data acquisition.
-360 degree static scanning
-Mainly used by Google Inc. for detecting the surroundings of the vehicle.
The Cruise System has:
-Cameras and Radars to map out surroundings(including other vehicles)
-Used mainly for highway scenarios
-Steering wheel motor mounted to steering column
-Adaptive speed control
-Collision Avoidance
-RP-1 Sensors
-Will be made in future for other vehicles
Type of algorithm a Self Driving car uses is:
The combination of 3-D imaging with multiple 1064 nm lasers, edge -detection algorithm, motion-detection algorithm and Tracking Algorithm.
Recommended Reading:  Chapter 8: Support Vector Machine
Next: 
To start reading from a topic of your choice, you can go back to the Table of Contents here
This course evolves with your active feedback. Do let us know your feedback in the comments section below.
Looking for jobs in Artificial Intelligence? Check here

TOASTED AND SERVED TO YOUR INBOX

* indicates required

      LaunchToast
      Logo
      Compare items
      • Total (0)
      Compare
      0
      Shopping cart