skip to main content

Explore Research Products in the NSF-PAR

Title: Hierarchical Neural Dynamic Policies
We tackle the problem of generalization to unseen configurations for dynamic tasks in the real world while learning from high-dimensional image input. The family of nonlinear dynamical system-based methods have successfully demonstrated dynamic robot behaviors but have difficulty in generalizing to unseen configurations as well as learning from image inputs. Recent works approach this issue by using deep network policies and reparameterize actions to embed the structure of dynamical systems but still struggle in domains with diverse configurations of image goals, and hence, find it difficult to generalize. In this paper, we address this dichotomy by leveraging embedding the structure of dynamical systems in a hierarchical deep policy learning framework, called Hierarchical Neural Dynamical Policies (H-NDPs). Instead of fitting deep dynamical systems to diverse data directly, H-NDPs form a curriculum by learning local dynamical system-based policies on small regions in state-space and then distill them into a global dynamical system-based policy that operates only from high-dimensional images. H-NDPs additionally provide smooth trajectories, a strong safety benefit in the real world. We perform extensive experiments on dynamic tasks both in the real world (digit writing, scooping, and pouring) and simulation (catching, throwing, picking). We show that H-NDPs are easily integrated with both imitation as well as reinforcement learning setups and achieve state-of-the-art results.  more » « less
Award ID(s):
2024594
NSF-PAR ID:
10312794
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Robotics: Science and Systems
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ( , Complexity)
    null (Ed.)
    We investigate the ways in which a machine learning architecture known as Reservoir Computing learns concepts such as “similar” and “different” and other relationships between image pairs and generalizes these concepts to previously unseen classes of data. We present two Reservoir Computing architectures, which loosely resemble neural dynamics, and show that a Reservoir Computer (RC) trained to identify relationships between image pairs drawn from a subset of training classes generalizes the learned relationships to substantially different classes unseen during training. We demonstrate our results on the simple MNIST handwritten digit database as well as a database of depth maps of visual scenes in videos taken from a moving camera. We consider image pair relationships such as images from the same class; images from the same class with one image superposed with noise, rotated 90°, blurred, or scaled; images from different classes. We observe that the reservoir acts as a nonlinear filter projecting the input into a higher dimensional space in which the relationships are separable; i.e., the reservoir system state trajectories display different dynamical patterns that reflect the corresponding input pair relationships. Thus, as opposed to training in the entire high-dimensional reservoir space, the RC only needs to learns characteristic features of these dynamical patterns, allowing it to perform well with very few training examples compared with conventional machine learning feed-forward techniques such as deep learning. In generalization tasks, we observe that RCs perform significantly better than state-of-the-art, feed-forward, pair-based architectures such as convolutional and deep Siamese Neural Networks (SNNs). We also show that RCs can not only generalize relationships, but also generalize combinations of relationships, providing robust and effective image pair classification. Our work helps bridge the gap between explainable machine learning with small datasets and biologically inspired analogy-based learning, pointing to new directions in the investigation of learning processes. 
    more » « less
  2. ; ; ; ; ; ; ( , Proceedings of Machine Learning Research)
    Deep generative models have enabled the automated synthesis of high-quality data for diverse applications. However, the most effective generative models are specialized to data from a single domain (e.g., images or text). Real-world applications such as healthcare require multi-modal data from multiple domains (e.g., both images and corresponding text), which are difficult to acquire due to limited availability and privacy concerns and are much harder to synthesize. To tackle this joint synthesis challenge, we propose an End-to-end MultImodal X-ray genERative model (EMIXER) for jointly synthesizing x-ray images and corresponding free-text reports, all conditional on diagnosis labels. EMIXER is an conditional generative adversarial model by 1) generating an image based on a label, 2) encoding the image to a hidden embedding, 3) producing the corresponding text via a hierarchical decoder from the image embedding, and 4) a joint discriminator for assessing both the image and the corresponding text. EMIXER also enables self-supervision to leverage vast amount of unlabeled data. Extensive experiments with real X-ray reports data illustrate how data augmentation using synthesized multimodal samples can improve the performance of a variety of supervised tasks including COVID-19 X-ray classification with very limited samples. The quality of generated images and reports are also confirmed by radiologists. We quantitatively show that EMIXER generated synthetic datasets can augment X-ray image classification, report generation models to achieve 5.94% and 6.9% improvement on models trained only on real data samples. Taken together, our results highlight the promise of state of generative models to advance clinical machine learning. 
    more » « less
  3. ; ; ; ; ; ; ; ( , The International Journal of Robotics Research)

    We present a strategy for simulation-to-real transfer, which builds on recent advances in robot skill decomposition. Rather than focusing on minimizing the simulation–reality gap, we propose a method for increasing the sample efficiency and robustness of existing simulation-to-real approaches which exploits hierarchy and online adaptation. Instead of learning a unique policy for each desired robotic task, we learn a diverse set of skills and their variations, and embed those skill variations in a continuously parameterized space. We then interpolate, search, and plan in this space to find a transferable policy which solves more complex, high-level tasks by combining low-level skills and their variations. In this work, we first characterize the behavior of this learned skill space, by experimenting with several techniques for composing pre-learned latent skills. We then discuss an algorithm which allows our method to perform long-horizon tasks never seen in simulation, by intelligently sequencing short-horizon latent skills. Our algorithm adapts to unseen tasks online by repeatedly choosing new skills from the latent space, using live sensor data and simulation to predict which latent skill will perform best next in the real world. Importantly, our method learns to control a real robot in joint-space to achieve these high-level tasks with little or no on-robot time, despite the fact that the low-level policies may not be perfectly transferable from simulation to real, and that the low-level skills were not trained on any examples of high-level tasks. In addition to our results indicating a lower sample complexity for families of tasks, we believe that our method provides a promising template for combining learning-based methods with proven classical robotics algorithms such as model-predictive control.

     
    more » « less
  4. ; ; ; ; ; ; ; ( , 2020 IEEE International Conference on Robotics and Automation (ICRA))
    null (Ed.)
    Robotic manipulation of deformable 1D objects such as ropes, cables, and hoses is challenging due to the lack of high-fidelity analytic models and large configuration spaces. Furthermore, learning end-to-end manipulation policies directly from images and physical interaction requires significant time on a robot and can fail to generalize across tasks. We address these challenges using interpretable deep visual representations for rope, extending recent work on dense object descriptors for robot manipulation. This facilitates the design of interpretable and transferable geometric policies built on top of the learned representations, decoupling visual reasoning and control. We present an approach that learns point-pair correspondences between initial and goal rope configurations, which implicitly encodes geometric structure, entirely in simulation from synthetic depth images. We demonstrate that the learned representation - dense depth object descriptors (DDODs) - can be used to manipulate a real rope into a variety of different arrangements either by learning from demonstrations or using interpretable geometric policies. In 50 trials of a knot-tying task with the ABB YuMi Robot, the system achieves a 66% knot-tying success rate from previously unseen configurations. See https://tinyurl.com/rope-learning for supplementary material and videos. 
    more » « less
  5. ; ; ; ; ( , The International Journal of Robotics Research)

    This paper tackles the task of goal-conditioned dynamic manipulation of deformable objects. This task is highly challenging due to its complex dynamics (introduced by object deformation and high-speed action) and strict task requirements (defined by a precise goal specification). To address these challenges, we present Iterative Residual Policy (IRP), a general learning framework applicable to repeatable tasks with complex dynamics. IRP learns an implicit policy via delta dynamics—instead of modeling the entire dynamical system and inferring actions from that model, IRP learns delta dynamics that predict the effects of delta action on the previously observed trajectory. When combined with adaptive action sampling, the system can quickly optimize its actions online to reach a specified goal. We demonstrate the effectiveness of IRP on two tasks: whipping a rope to hit a target point and swinging a cloth to reach a target pose. Despite being trained only in simulation on a fixed robot setup, IRP is able to efficiently generalize to noisy real-world dynamics, new objects with unseen physical properties, and even different robot hardware embodiments, demonstrating its excellent generalization capability relative to alternative approaches.

     
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email