Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

University of Waterloo

$31,000.00

Motion primitives for understanding and learning human behaviour

FY 2014-15

Summary
Today's robots operate primarily in industrial settings, where interaction between robots and humans is limited. Recently, there has been a significant research initiative to develop robots suitable for direct interaction with human users, in applications such as domestic service robots, assistants to the elderly, security robots, entertainment robots, etc. The objective of this research is to enable robots to operate in human environments, by developing algorithms for online analysis and understanding of human movement and behaviour, allowing robots to interact and cooperate with human partners in an intuitive and safe manner.Human motion is composed of movement primitives, atomic actions which are the basic building blocks of larger, more complex behaviours. This proposal will develop methods for autonomously learning movement primitives and their relations during online observation of human motion. Using knowledge of movement primitives and their sequencing, we will also develop algorithms for predicting future motions and inferring the likely goals and intentions of observed human actions. The proposed approach will improve safety during interaction, as robots will be better able to predict human behaviour and respond accordingly. Moreover, robots will be able to offer assistance congruent with the current goals, anticipating the needs of the user and providing an intuitive and human-like interaction. Finally, by learning and imitating motions observed from human operators, the robot can expand its repertoire of abilities and adapt to changes in the environment. The majority of the proposed budget is targeted at student support, providing significant opportunities for student research and training. A unique feature of the proposal are online learning algorithms. This approach enables the robot to learn continuously through interaction with a human teacher and provide immediate feedback, allowing people to teach new skills to robots intuitively, in the same way they teach other people. The proposed algorithms have applications beyond robotics, including activity recognition, assisting the elderly, and motion analysis for sports training and rehabilitation.
Program
Discovery Grants Program - Individual
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
386697-2010
Name nom
Kulic, Danica
Department département
Electrical & Computer Engineering
Organization id
33
Institution établissement
University of Waterloo
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2014
Competition year année de concours
2010
Award amount
31000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
1510
Committee name en
Electrical and Computer Engineering
Committee name fr
Génie électrique et informatique
Area of application code
1200
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Advancement of knowledge
Area of application fr
Avancement des connaissances
Research subject code
2510
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Adaptive, learning and evolutionary systems
Research subject fr
Systèmes d'apprentissage adaptatifs et évolutifs
Partie
5
Nb partie
5
Application title
Motion primitives for understanding and learning human behaviour
Keyword
NSERC
Application summary
Today's robots operate primarily in industrial settings, where interaction between robots and humans is limited. Recently, there has been a significant research initiative to develop robots suitable for direct interaction with human users, in applications such as domestic service robots, assistants to the elderly, security robots, entertainment robots, etc. The objective of this research is to enable robots to operate in human environments, by developing algorithms for online analysis and understanding of human movement and behaviour, allowing robots to interact and cooperate with human partners in an intuitive and safe manner.Human motion is composed of movement primitives, atomic actions which are the basic building blocks of larger, more complex behaviours. This proposal will develop methods for autonomously learning movement primitives and their relations during online observation of human motion. Using knowledge of movement primitives and their sequencing, we will also develop algorithms for predicting future motions and inferring the likely goals and intentions of observed human actions. The proposed approach will improve safety during interaction, as robots will be better able to predict human behaviour and respond accordingly. Moreover, robots will be able to offer assistance congruent with the current goals, anticipating the needs of the user and providing an intuitive and human-like interaction. Finally, by learning and imitating motions observed from human operators, the robot can expand its repertoire of abilities and adapt to changes in the environment. The majority of the proposed budget is targeted at student support, providing significant opportunities for student research and training. A unique feature of the proposal are online learning algorithms. This approach enables the robot to learn continuously through interaction with a human teacher and provide immediate feedback, allowing people to teach new skills to robots intuitively, in the same way they teach other people. The proposed algorithms have applications beyond robotics, including activity recognition, assisting the elderly, and motion analysis for sports training and rehabilitation.