The Hardware Design of the Humanoid Robot RO-PE and the Self-localization Algorithm in RoboCup

1
The Hardware Design of the Humanoid Robot RO-PE
and the Self-localization Algorithm in RoboCup

• Tian Bo
• Control and Mechatronics Lab
• Mechanical Engineering
• 20 Feb 2009 SMC

2
RoboCup and Team RO-PE

• RoboCupTM
• is an international joint project to promote
  artificial intelligence and robotics.
• Team RO-PE
• RO-PE (RObot for Personal Entertainment) is a
  series of small size humanoid robots developed by
  the Legged Locomotion Group

3
Highlight
4
Design of the Robot
5
Hierarchy of the System
6
Self-localization in RoboCup

• Global localization problem

• The robot is not told its initial pose, but has
  to determine it from the very beginning

7
Self-localization in RoboCup

• Global localization problem
• Kidnapped robot problem

• - a well-localized robot is teleported to some
  other position without being told

• - The kidnapped robot problem is often used to
  test a robots ability to recover autonomously
  form catastrophic localization failures

8
Self-localization in RoboCup

• Global localization problem
• Kidnapped robot problem
• Other difficulties in the humanoid soccer
  scenario

- The field of view is limited, due to the
human-likesensor.- Noisy perceptions and noisy
odometry. - Computational resources are limited.
But data needs to be processed in real-time.
9
What is Particle Filter

• Belongs to the family of Bayesian Filters (Bayes
  Filter,Kalman Filter)
• Bayesian filter techniques provide a powerful
  statistical tool to help manage measurement
  uncertainty
• Based on the knowledge of previous state,
  Bayesian filter probabilistically estimates a
  dynamic systems state from noisy environment.

10
What is Particle Filter

• Particle filters represent beliefs by a sets of
  samples, or particles
• It is a probabilistic approach, in which the
  current location of the modeled as a density of
  the particles.
• Each particle can be seen as the hypotheses of
  the robot being located at this posture.

11
What is Particle Filter

• The main objective of particle filtering is to
  track a variable of interest as it evolves over
  time, typically with a non-Gaussian and
  potentially multi-modal pdf
• The particle filter algorithm is recursive in
  nature and operates in two phases prediction and
  update

12
Particle Filter Localization
Move all the particles according to the motion
model of the previous action of the robot
More practical part
Determine the probabilities qi based on
observation model
(real trick)
Resampling
13
Particle Filter Algorithm
(Probabilistic Robotics, C4 P98)
14
Particle Filter for Self-Localization

• Loop
• initializeParticles() //pi (x, y, theta, w)
• While(sensor reset ! 1)
• motionModel()
• sensorModel()
• updateWeight()
• resampling()
• output()

15
Initialization
16
Motion Model

• This is the prediction part
• The particle filter for self-localization
  estimates the robots pose
• Odometry-based Method
• Take x for example
• pm.x pm.x deltaX (1gaussian)

17
Motion Model

• Simplified Leg Model
• Step 1
• hip_yaw 0

18
Motion Model

• Simplified Leg Model
• Step 2
• hip_yaw ?

19
Motion Model

• We do localization when the left leg just touch
  theground
• This odometry gets the data from the motion
  commend sent to servo,it will not be affected
  bythe control signal. It can be more accurate
  if the servo can feedback its position.

20
Error for the Motion Model(1)
with the steps increased, the error increase.
The largest error is 25, happens at the 14th
step.
21
Error for the Motion Model(2)
Like walking motion, the real distance has a
linear relationship with the number of steps, so
we can achieve better results through improve our
model or make correction.
Back to Particle Filter
22
Sensor Model

• This is the update part
• In the whole field, we only use the two goals and
  two poles for self-localization. The world model
  is known.
• We only take the angle from the landmark to the
  front of robot into consideration

23
Sensor Model

• We are only using the wide angle camera for
  landmark recognition, the information we can
  abstract from the camera is limited.

24
Sensor Model

• Once a landmark is observed by the robot, the
  function sensorModel() will be executed. The
  weight for every particle will be updated
  accordingly.
• If several landmarks are observed at once, the
  weight will be

25
Sensor Model

• We can get the expectedTheta through the position
  and orientation of the particle and the world
  model
• if(blue_goal_found)
• /we can get the percievedTheta from camera, the
  coordination of the landmark on the image, and
  the position of the panning servo of the head /
• updateWeight(blue_goal)

26
Sensor Model

• Update Weight
• deltaTheta fabs ( expectedTheta
  perceivedTheta)
• belief distribution ( deltaTheta )
• pi.weight pi.weight belief
• Normalize(pi.weight)
• Distribution Policy
• Now we are using Gaussian distribution.

27
Resampling

• The simplest method of resampling is to select
  each particle with a probability equal to its
  weight.
• Select with Replacement
• Linear time Resampling
• Resampling by Liu et al.

28
Resampling
(A Particle Filter Tutorial for Mobile Robot
Localization TR-CIM-04-02)
29
Final Estimation

• Finding the Largest Cluster
• Give the best result but computational expensive
• Calculating the Average
• May affect by the far away particles
• Best Weight
• Fastest way to give the result, suitable for the
  real-time system

30
Future work

• Find out the condition to make sensor resetting,
  or else sometimes the particle will converge to a
  false point and cannot recover.
• Including the distance information in sensor
  model.
• Try new resampling and weightUpdate algorithm.

31
(No Transcript)
32
(No Transcript)
33
(No Transcript)
34
Thank you