Probabilistic movement modeling for intention inference in human–robot interaction

Wang, Zhikun; Mülling, Katharina; Deisenroth, Marc Peter; Amor, Heni Ben; Vogt, David; Schoelkopf, Bernhard; Peters, Jan

doi:10.1177/0278364913478447

Cited by 141 publications

(81 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to our work, the output of our method is a movement primitive that is intrinsically correlated to the human action and can be used to directly control the robot. Wang et al (2013) proposed an intention-driven dynamics model to encode human intentions as latent states in a graphical model. Intentions can be modeled as discrete variables, such as action labels, or continuous variables, such as an object's final position.…”

Section: Action and Intention Recognitionmentioning

confidence: 99%

Probabilistic movement primitives for coordination of multiple human–robot collaborative tasks

et al. 2016

Self Cite

View full text Add to dashboard Cite

This paper proposes an interaction learning method for collaborative and assistive robots based on movement primitives. The method allows for both action recognition and human-robot movement coordination. It uses imitation learning to construct a mixture model of human-robot interaction primitives. This probabilistic model allows the assistive trajectory of the robot to be inferred from human observations. The method is scalable in relation to the number of tasks and can learn nonlinear correlations between the trajectories that describe the human-robot interaction. We evaluated the method experimentally with a lightweight robot arm in a variety of assistive scenarios, including the coordinated handover of a bottle to a human, and the collaborative assembly of a toolbox. Potential applications of the method are personal caregiver robots, control of intelligent prosthetic devices, and robot coworkers in factories.Keywords Movement primitives · physical humanrobot interaction · imitation learning · mixture model · action recognition · trajectory generation

show abstract

Section: Action and Intention Recognitionmentioning

confidence: 99%

Probabilistic movement primitives for coordination of multiple human–robot collaborative tasks

et al. 2016

Self Cite

View full text Add to dashboard Cite

show abstract

“…Tanaka et al [9] use a Markov model to predict the positions of a worker in an assembly line. Wang et al [10] propose the Intention-Driven Dynamics Model (IDDM) as a probabilistic graphical model with observations, latent states and intentions where the transitions between latent states and the mapping from latent states to observations are modeled as Gaussian Processes. Koppula et al [11] use a conditional random field with sub-activities, human poses, object affordances and object locations over time.…”

Section: Related Workmentioning

confidence: 99%

Learning multiple collaborative tasks with a mixture of Interaction Primitives

Ewerton

Neumann

Lioutikov

et al. 2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Abstract-Robots that interact with humans must learn to not only adapt to different human partners but also to new interactions. Such a form of learning can be achieved by demonstrations and imitation. A recently introduced method to learn interactions from demonstrations is the framework of Interaction Primitives. While this framework is limited to represent and generalize a single interaction pattern, in practice, interactions between a human and a robot can consist of many different patterns. To overcome this limitation this paper proposes a Mixture of Interaction Primitives to learn multiple interaction patterns from unlabeled demonstrations. Specifically the proposed method uses Gaussian Mixture Models of Interaction Primitives to model nonlinear correlations between the movements of the different agents. We validate our algorithm with two experiments involving interactive tasks between a human and a lightweight robotic arm. In the first, we compare our proposed method with conventional Interaction Primitives in a toy problem scenario where the robot and the human are not linearly correlated. In the second, we present a proof-of-concept experiment where the robot assists a human in assembling a box.

show abstract

“…Inference on the graphical model, allows a robot to anticipate human activity and choose a corresponding, preprogrammed robot response. Wang et al [10] propose the intention-driven dynamics model, which models human intentions as latent states in graphical model. Intentions can be modeled as discrete variables, e.g., action labels, or continuous variables, e.g., an object's final position.…”

Section: Related Workmentioning

confidence: 99%

Learning interaction for collaborative tasks with probabilistic movement primitives

Maeda

Ewerton

Lioutikov

et al. 2014

2014 IEEE-RAS International Conference on Humanoid Robots

Self Cite

View full text Add to dashboard Cite

Abstract-This paper proposes a probabilistic framework based on movement primitives for robots that work in collaboration with a human coworker. Since the human coworker can execute a variety of unforeseen tasks a requirement of our system is that the robot assistant must be able to adapt and learn new skills on-demand, without the need of an expert programmer. Thus, this paper leverages on the framework of imitation learning and its application to human-robot interaction using the concept of Interaction Primitives (IPs). We introduce the use of Probabilistic Movement Primitives (ProMPs) to devise an interaction method that both recognizes the action of a human and generates the appropriate movement primitive of the robot assistant. We evaluate our method on experiments using a lightweight arm interacting with a human partner and also using motion capture trajectories of two humans assembling a box. The advantages of ProMPs in relation to the original formulation for interaction are exposed and compared.

show abstract

Probabilistic movement modeling for intention inference in human–robot interaction

Cited by 141 publications

References 44 publications

Probabilistic movement primitives for coordination of multiple human–robot collaborative tasks

Probabilistic movement primitives for coordination of multiple human–robot collaborative tasks

Learning multiple collaborative tasks with a mixture of Interaction Primitives

Learning interaction for collaborative tasks with probabilistic movement primitives

Contact Info

Product

Resources

About