Timezone: »

Dynamic Environments with Deformable Objects
Rika Antonova · peiyang shi · Hang Yin · Zehang Weng · Danica Kragic

We propose a set of environments with dynamic tasks that involve highly deformable topologically non-trivial objects. These environments facilitate easy experimentation: offer fast runtime, support large-scale parallel data generation, are easy to connect to reinforcement learning frameworks with OpenAI Gym API. We offer several types of benchmark tasks with varying levels of complexity, provide variants with procedurally generated cloth objects and randomized material textures. Moreover, we allow users to customize the tasks: import custom objects and textures, adjust size and material properties of deformable objects.We prioritize dynamic aspects of the tasks: forgoing 2D tabletop manipulation in favor of 3D tasks, with gravity and inertia playing a non-negligible role. Such advanced challenges require insights from multiple fields: machine learning and computer vision to process high-dimensional inputs, methods from computer graphics and topology to inspire structured and interpretable representations, insights from robotics to learn advanced control policies. We aim to help researches from these fields contribute their insights and simplify establishing interdisciplinary collaborations.

Author Information

Rika Antonova (Stanford University)

Rika is a postdoc at [Stanford IPRL](http://iprl.stanford.edu/#people) lab, part of NSF/CRA [CI Fellowship](https://cifellows2020.org/2020-class/) program, doing research on active learning of [transferable priors, kernels, and latent representations for robotics](https://cccblog.org/2021/05/26/active-learning-of-transferable-priors-kernels-and-latent-representations-for-robotics/). Rika completed her PhD work on [data-efficient simulation-to-reality transfer](http://kth.diva-portal.org/smash/record.jsf?pid=diva2:1476620) at the Robotics, Perception and Learning lab in KTH, Stockholm, in the group headed by Danica Kragic. Before that, Rika was a Masters student at the Robotics Institute at Carnegie Mellon University, developing Bayesian optimization approaches for learning control parameters for bipedal locomotion (with Akshara Rai and Chris Atkeson). Rika's CMU MS advisor was Emma Brunskill and in her group Rika worked on developing reinforcement learning algorithms for education. A few years earlier, Rika was a software engineer at Google, first in the Search Personalization group and then in the Character Recognition team (developing open-source OCR engine Tesseract).

peiyang shi (KTH Royal Institute of Technology)
Hang Yin (KTH Royal Institute of Technology, Stockholm, Sweden)
Zehang Weng (KTH)
Danica Kragic (KTH Royal Institute of Technology)

More from the Same Authors