skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Charting the trade-off between design complexity and plan execution under probabilistic actions
Practical robot designs must strike a compromise between fabrication/manufacture cost and anticipated execution performance. Compared to parsimonious designs, more capable (and hence more expensive) robots generally achieve their ends with greater efficiency. This paper examines how the roboticist might explore the space of designs to gain an understanding of such trade-offs. We focus, specifically, on design choices that alter the set of actions available to the robot, and model those actions as involving uncertainty. We consider planning problems under the Markov Decision Process (MDP) model, which leads us to examine how to relate the cost of some design to the expected cost of an execution for the optimal policies feasible with that design. The complexity of this problem –-expressed via hardness in the fixed parameter tractability sense–- depends on the number of actions to choose from. When that number is not negligible, we give a novel representation and an algorithm utilizing that structure that allows useful savings over naive enumeration.  more » « less
Award ID(s):
1849291
PAR ID:
10333046
Author(s) / Creator(s):
Date Published:
Journal Name:
IEEE International Conference on Robotics and Automation
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, Frontiers in robotics and AI)
    null (Ed.)
    There has been an explosion of ideas in soft robotics over the past decade, resulting in unprecedented opportunities for end effector design. Soft robot hands offer benefits of low-cost, compliance, and customized design, with the promise of dexterity and robustness. The space of opportunities is vast and exciting. However, new tools are needed to understand the capabilities of such manipulators and to facilitate manipulation planning with soft manipulators that exhibit free-form deformations. To address this challenge, we introduce a sampling based approach to discover and model continuous families of manipulations for soft robot hands. We give an overview of the soft foam robots in production in our lab and describe novel algorithms developed to characterize manipulation families for such robots. Our approach consists of sampling a space of manipulation actions, constructing Gaussian Mixture Model representations covering successful regions, and refining the results to create continuous successful regions representing the manipulation family. The space of manipulation actions is very high dimensional; we consider models with and without dimensionality reduction and provide a rigorous approach to compare models across different dimensions by comparing coverage of an unbiased test dataset in the full dimensional parameter space. Results show that some dimensionality reduction is typically useful in populating the models, but without our technique, the amount of dimensionality reduction to use is difficult to predict ahead of time and can depend on the hand and task. The models we produce can be used to plan and carry out successful, robust manipulation actions and to compare competing robot hand designs. 
    more » « less
  2. ; (, The International Journal of Robotics Research)
    Having a well-rounded fixed leg design for a quadruped inevitably limits performance across diverse tasks, while tunability enables specialization and leads to better performance. This paper introduces a sub-500-gram quadruped robot with a rich leg design space. Made with laminate design and fabrication techniques, its legs have a range of tunable design parameters, including leg length, transmission ratio, and passive parallel and series stiffness. The legs are also straightforward to model, low-cost, and fast to manufacture. We propose methods to span the leg’s feasible design space and construct simulation environments for training a locomotion policy with reinforcement learning to remove the need for manual controller design and tuning. This policy not only works across leg designs but also exploits the unique dynamics of each leg for better locomotion. A curation process is employed to select designs given performance goals, which is more interpretable than optimization and provides insights for design improvements and discoveries of design principles. Thanks to the tight integration of design, fabrication, simulation, and control, our proposed pipeline produces leg designs with performance that aligns with the simulation, while the learned locomotion policy can be used successfully on the real robot. The fast longitudinal running design reaches a maximum speed of 0.7 m/s or 5.4 body lengths per second, and the low cost of transport (COT) design has a COT of 0.3. 
    more » « less
  3. ; ; ; ; ; (, MICRO '52: Proceedings of the 52nd Annual IEEE/ACM International Symposium on Microarchitecture)
    null (Ed.)
    The data partitioning and scheduling strategies used by DNN accelerators to leverage reuse and perform staging are known as dataflow, which directly impacts the performance and energy efficiency of DNN accelerators. An accelerator micro architecture dictates the dataflow(s) that can be employed to execute layers in a DNN. Selecting a dataflow for a layer can have a large impact on utilization and energy efficiency, but there is a lack of understanding on the choices and consequences of dataflow, and of tools and methodologies to help architects explore the co-optimization design space. In this work, we first introduce a set of data-centric directives to concisely specify the DNN dataflow space in a compiler-friendly form. We then show how these directives can be analyzed to infer various forms of reuse and to exploit them using hardware capabilities. We codify this analysis into an analytical cost model, MAESTRO (Modeling Accelerator Efficiency via Patio-Temporal Reuse and Occupancy), that estimates various cost-benefit tradeoffs of a dataflow including execution time and energy efficiency for a DNN model and hardware configuration. We demonstrate the use of MAESTRO to drive a hardware design space exploration experiment, which searches across 480M designs to identify 2.5M valid designs at an average rate of 0.17M designs per second, including Pareto-optimal throughput- and energy-optimized design points. 
    more » « less
  4. ; (, TU Wien Academic Press, Wien)
    Nadel, Alexander; Rozier, Kristin Yvonne (Ed.)
    Symbolic execution is a powerful verification tool for hardware designs, in particular for security validation. However, symbolic execution suffers from the path explosion problem in which the number of paths to explore grows exponentially with the number of branches in the design. We introduce a new approach, piecewise composition, which leverages the modular structure of hardware to transfer the work of path exploration to SMT solvers. Piecewise composition works by recognizing that independent parts of a design can each be explored once, and the exploration reused. A hardware design with N independent always blocks and at most b branch points per block will require exploration of O((2^b)N) paths in a single clock cycle with our approach compared to O(2^(bN)) paths using traditional symbolic execution. We present Sylvia, a symbolic execution engine implementing piecewise composition. The engine operates directly over RTL without requiring translation to a netlist or software simulation. We evaluate our tool on multiple open-source SoC and CPU designs, including the OR1200 and PULPissimo RISC-V SoC. The piecewise composition technique reduces the number of paths explored by an order of magnitude and reduces the runtime by 97% compared to our baseline. Using 84 properties from the security literature we find assertion violations in open-source designs that traditional model checking and formal verification tools do not find. 
    more » « less
  5. ; ; (, IEEE Transactions on Robotics)
    Task and motion planning represents a powerful set of hybrid planning methods that combine reasoning over discrete task domains and continuous motion generation. Traditional reasoning necessitates task domain models and enough information to ground actions to motion planning queries. Gaps in this knowledge often arise from sources like occlusion or imprecise modeling. This work generates task and motion plans that include actions cannot be fully grounded at planning time. During execution, such an action is handled by a provided human designed or learned closed-loop behavior. Execution combines offline planned motions and online behaviors till reaching the task goal. Failures of behaviors are fed back as constraints to find new plans. Forty real-robot trials and motivating demonstrations are performed to evaluate the proposed framework and compare against state-of-the-art. Results show faster execution time, less number of actions, and more success in problems where diverse gaps arise. The experiment data is shared for researchers to simulate these settings. The work shows promise in expanding the applicable class of realistic partially grounded problems that robots can address. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email