Rozo, L., Calinon, S. and Caldwell, D.G. (2014)
Learning Force and Position Constraints in Human-robot Cooperative Transportation
In Proc. of the IEEE Intl Symp. on Robot and Human Interactive Communication (Ro-Man), Edinburgh, Scotland, UK, pp. 619-624.


Physical interaction between humans and robots arises a large set of challenging problems involving hardware, safety, control and cognitive aspects, among others. In this context, the cooperative (two or more people/robots) transportation of bulky loads in manufacturing plants is a practical example where these challenges are evident. In this paper, we address the problem of teaching a robot collaborative behaviors from human demonstrations. Specifically, we present an approach that combines: probabilistic learning and dynamical systems, to encode the robot's motion along the task. Our method allows us to learn not only a desired path to take the object through, but also, the force the robot needs to apply to the load during the interaction. Moreover, the robot is able to learn and reproduce the task with varying initial and final locations of the object. The proposed approach can be used in scenarios where not only the path to be followed by the transported object matters, but also the force applied to it. Tests were successfully carried out in a scenario where a 7 DOFs backdrivable manipulator learns to cooperate, with a human, to transport an object while satisfying the position and force constraints of the task.

Bibtex reference

  author="Rozo, L. and Calinon, S. and Caldwell, D. G.",
  title="Learning Force and Position Constraints in Human-robot Cooperative Transportation",
  booktitle = "Proc. {IEEE} Intl Symposium on Robot and Human Interactive Communication ({Ro-Man})",
  address="Edinburgh, Scotland, UK",


This video shows the experimental results of a learning approach in human-robot cooperative transportation task.

Demonstration phase Reproduction phase

Source codes

Demonstration a task-parameterized probabilistic model encoding movements in the form of virtual spring-damper systems acting in multiple frames of reference. Each candidate coordinate system observes a set of demonstrations from its own perspective, by extracting an attractor path whose variations depend on the relevance of the frame through the task. This information is exploited to generate a new attractor path corresponding to new situations (new positions and orientation of the frames), while the predicted covariances are exploited by a linear quadratic regulator (LQR) to estimate the stiffness and damping feedback terms of the spring-damper systems, resulting in a minimal intervention control strategy.


Download task-parameterized tensor GMM with LQR sourcecode


Unzip the file and run 'demo01' in Matlab. Several reproduction algorithms can be selected by commenting/uncommenting lines 89-91 and 110-112 in demo01.m (finite/infinite horizon LQR or dynamical system with constant gains). 'demo_testLQR01' and 'demo_testLQR02' can also be run as examples of LQR.


Go back to the list of publications