PrincetonComputer SciencePIXL GroupPublications → [Wu et al. 2020] Local Access
Spatial Action Maps for Mobile Manipulation

arXiv preprint, April 2020

Jimmy Wu, Xingyuan Sun, Andy Zeng,
Shuran Song, Johnny Lee,
Szymon Rusinkiewicz, Thomas Funkhouser
Abstract

This paper proposes a new action representation for learning to perform complex mobile manipulation tasks. In a typical deep Q-learning setup, a convolutional neural network (ConvNet) is trained to map from an image representing the current state (e.g., a birds-eye view of a SLAM reconstruction of the scene) to predicted Q-values for a small set of steering command actions (step forward, turn right, turn left, etc.). Instead, we propose an action representation in the same domain as the state: "spatial action maps." In our proposal, the set of possible actions is represented by pixels of an image, where each pixel represents a trajectory to the corresponding scene location along a shortest path through obstacles of the partially reconstructed scene. A significant advantage of this approach is that the spatial position of each state-action value prediction represents a local milestone (local end-point) for the agent's policy, which may be easily recognizable in local visual patterns of the state image. A second advantage is that atomic actions can perform long-range plans (follow the shortest path to a point on the other side of the scene), and thus it is simpler to learn complex behaviors with a deep Q-network. A third advantage is that we can use a fully convolutional network (FCN) with skip connections to learn the mapping from state images to pixel-aligned action images efficiently. During experiments with a robot that learns to push objects to a goal location, we find that policies learned with this proposed action representation achieve significantly better performance than traditional alternatives.
Citation

Jimmy Wu, Xingyuan Sun, Andy Zeng, Shuran Song, Johnny Lee, Szymon Rusinkiewicz, and Thomas Funkhouser.
"Spatial Action Maps for Mobile Manipulation."
arXiv:2004.09141, April 2020.

BibTeX

@techreport{Wu:2020:SAM,
   author = "Jimmy Wu and Xingyuan Sun and Andy Zeng and Shuran Song and Johnny Lee
      and Szymon Rusinkiewicz and Thomas Funkhouser",
   title = "Spatial Action Maps for Mobile Manipulation",
   institution = "arXiv preprint",
   year = "2020",
   month = apr,
   number = "2004.09141"
}