Download presentation
1
VEHICLE INTELLIGENCE LAB
Chapter 11. A Bayesian model of imitation in infants and robots (2/2) in Imitation and Social Learning in Robots, Humans and Animals, Nehaniv & Dautenhahn Course: Robots Learning from Humans Dong-Kyoung Kye Vehicle Intelligence Laboratory School of Electrical and Computer Engineering Seoul National University
2
Contents Bayesian imitative learning
Example : learning to solve a maze task through imitation Learning a forward model for the maze task Imitation using the learned forward model and learned priors Inferring the intent of the teacher Further applications in robotic learning Towards a probabilistic model for imitation in infants Conclusion
3
Bayesian imitative learning - Forward model
It maps state, action to next state : π π π‘ π π‘ , π΄ π‘ ) Learned from exploring the state-space at random Body babbling Supervised process (Assuming proprioception)
4
Bayesian imitative learning - Inverse model
Probability that an action is chosen given the desired next state, and the goal π π΄ π‘ π π‘ , π π‘+1 , π π ) π· π¨ π πΊ π , πΊ π+π , πΊ π ) βπ· πΊ π+π πΊ π , π¨ π )βπ· π¨ π πΊ π , πΊ π ) Forward model Prior
5
Learning to solve a maze task through imitation
Learning a forward model for the maze task 20 x 20 grid of squares States π π‘ : Grid locations in the maze Five actions available - North(N), East(E), South(S), West(W) or remain in place(X) The noisy βforward dynamicsβ of the environment - Actual and learned probabilistic forward models - Simulated maze environment
6
Learning to solve a maze task through imitation
Imitation using the learned forward model and learned priors The imitator can use βinverse modelβ to select appropriate actions to imitate the teacher and reach the goal state. π· π¨ π πΊ π , πΊ π+π , πΊ π ) βπ· πΊ π+π πΊ π , π¨ π )βπ· π¨ π πΊ π , πΊ π ) Inverse model Forward model Prior
7
Learning to solve a maze task through imitation
Imitation using the learned forward model and learned priors The imitator can use βinverse modelβ to select appropriate actions to imitate the teacher and reach the goal state. π· π¨ π πΊ π , πΊ π+π , πΊ π ) βπ· πΊ π+π πΊ π , π¨ π )βπ· π¨ π πΊ π , πΊ π ) Prior - Simulated maze environment
8
Learning to solve a maze task through imitation
Imitation using the learned forward model and learned priors
9
Learning to solve a maze task through imitation
Inferring the intent of the teacher The intent inference algorithm provides an estimate of the distribution over the instructorβs possible goals for each time step. π· πΊ π π¨ π , πΊ π , πΊ π+π )βπ· πΊ π+π πΊ π , π¨ π , πΊ π )βπ· π¨ π πΊ π , πΊ π )βπ· πΊ π πΊ π )βπ· (πΊ π ) Learned forward model Learned prior over actions
10
Learning to solve a maze task through imitation
With a maze task example.. It shows that how the abstract probabilistic framework proposed in this chapter can be used to solve a concrete sensorimotor problem.
11
Further applications in robotic learning
E.g.) Box lifting (HOAP-2)
12
Further applications in robotic learning
E.g.) Box lifting (HOAP-2) Learning forward models from motion capture. (a) Forward models learned by the system after observing 3 different actions performed by the human (b) Forward model learned by the system for the box lift experiment
13
Further applications in robotic learning
E.g.) Box lifting (HOAP-2)
14
Towards a probabilistic model for imitation in infants
- Active Intermodal Mapping (AIM)
15
Towards a probabilistic model for imitation in infants
- Match and correction process is the Bayesian action selection method.
16
Conclusion Bayesian approach is well-suited to imitation learning in real-world robotic environments which are noisy and uncertain Bayesian probabilistic framework can also be applied to better understand the stages of infant imitation learning.
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.