Skip to content

Guilherme Maeda

Research scientist in robot learning at the ATR Computational Neuroscience Laboratories.

  • Home
  • About/CV
  • Research
  • Publications
  • Code
  • Videos
  • Contact

Category: Video

Online optimal trajectory generation for robot table tennis (RAS 2018)

Koc, O.; Maeda, G.; Peters, J. (2018). “Online optimal trajectory generation for robot table tennis”. Robotics and Autonomous Systems (RAS). … More

Human-robot joint skill learning

One of the most successful recipes in robot learning is to initialize the robot with a *good policy* via imitation … More

Presenting at the Conference on Robot Learning (CoRL) 2017

November 2017. I am presenting our most recent work at the 1st Annual Conference on Robot Learning (CoRL 2017). The paper can … More

Active Incremental Learning of Robot Movement Primitives (PMLR/CoRL 2017)

Robots that can be programmed by non-technical users must be capable of learning new tasks incrementally, via demonstrations. This poses the … More

Ergonomics in robot trajectory generation (IROS 2017)

In collaboration with the Flowers Group in Inria, we addressed the problem of how to generate robot motions that are … More

Optimizing the Mapping from Human Observations to Robot Kinematics (IEEE RA-L 2016)

  Imitation learning is useful to endow robots with skills that are difficult, if not impossible, to program by hand. … More

Phase Estimation of Human Movements for Responsive Human-Robot Collaboration (ISRR 2015)

While probabilistic models are useful to classify and infer trajectories, a common problem is that their construction usually requires the … More

Interaction ProMPs (IJRR 2017, AURO 2016, HUMANOIDS 2014)

Interaction Probabilistic Movement Primitive (Interaction ProMP) is a probabilistic framework based on Movement Primitives that allows for both human action … More

  • Home
  • About/CV
  • Research
  • Publications
  • Code
  • Videos
  • Contact
WordPress.com.
Cancel