• Corpus ID: 244714577

SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot Learning

@inproceedings{Lv2021SAGCISystemTS,
  title={SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot Learning},
  author={Jun Lv and Qiaojun Yu and Lin Shao and Wenhai Liu and Wenqiang Xu and Cewu Lu},
  year={2021}
}
—Building general-purpose robots to perform a diverse range of tasks in a large variety of environments in the physical world at the human level is extremely challenging. According to [1], it requires the robot learning to be sample-efficient, generalizable, compositional, and incremental. In this work, we introduce a systematic learning framework called SAGCI-system towards achieving these above four requirements. Our system first takes the raw point clouds gathered by the camera mounted on… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 57 REFERENCES
SAPIEN: A SimulAted Part-Based Interactive ENvironment
  • Fanbo Xiang, Yuzhe Qin, Hao Su
  • Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
TLDR
SAPIEN is a realistic and physics-rich simulated environment that hosts a large-scale set of articulated objects that enables various robotic vision and interaction tasks that require detailed part-level understanding and hopes it will open research directions yet to be explored.
The foundation of efficient robot learning
TLDR
It will take a combination of new algorithmic techniques, inspiration from natural systems, and multiple levels of machine learning to revolutionize robotics with general-purpose intelligence.
Probabilistic Segmentation and Targeted Exploration of Objects in Cluttered Environments
TLDR
Evaluations show that the proposed information-theoretic approach allows a robot to efficiently determine the composite structure of its environment, and the probabilistic model allows straightforward integration of multiple modalities, such as movement data and static scene features.
Online interactive perception of articulated objects with multi-level recursive estimation based on task-specific priors
  • R. M. Martin, O. Brock
  • Computer Science
    2014 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2014
TLDR
An RGB-D-based online algorithm for the interactive perception of articulated objects that decomposes the perception problem into three interconnected levels of recursive estimation and shows how the perceptual skill can be used online to control the robot's behavior in real-world manipulation tasks.
Solving Rubik's Cube with a Robot Hand
TLDR
It is demonstrated that models trained only in simulation can be used to solve a manipulation problem of unprecedented complexity on a real robot, made possible by a novel algorithm, which is called automatic domain randomization (ADR), and a robot platform built for machine learning.
A Compositional Object-Based Approach to Learning Physical Dynamics
TLDR
The NPE's compositional representation of the structure in physical interactions improves its ability to predict movement, generalize across variable object count and different scene configurations, and infer latent properties of objects such as mass.
Interactive environment exploration in clutter
TLDR
This paper investigates the idea of exploring a small, bounded environment by prehensile and non-prehensile manipulation of the objects it contains by presenting an implementation on the PR2 robot and using it for object search in clutter.
Integrating visual perception and manipulation for autonomous learning of object representations
TLDR
A paradigm that integrates the robot’s manipulation and sensing capabilities to detect a new, previously unknown object and learn its visual appearance and the feasibility of the proposed approach is demonstrated by applying it to the problem of autonomous learning of visual representations for viewpoint-independent object recognition on a humanoid robot.
Interaction Networks for Learning about Objects, Relations and Physics
TLDR
The interaction network is introduced, a model which can reason about how objects in complex systems interact, supporting dynamical predictions, as well as inferences about the abstract properties of the system, and is implemented using deep neural networks.
Benchmarking Model-Based Reinforcement Learning
TLDR
This paper gathers a wide collection of MBRL algorithms and proposes over 18 benchmarking environments specially designed for MBRL, and describes three key research challenges for future MBRL research: the dynamics bottleneck, the planning horizon dilemma, and the early-termination dilemma.
...
1
2
3
4
5
...