skip to main content

Explore Research Products in the NSF-PAR

Title: Efficient Concurrent Design of the Morphology of Unmanned Aerial Systems and their Collective-Search Behavior
The collective operation of robots, such as unmanned aerial vehicles (UAVs) operating as a team or swarm, is affected by their individual capabilities, which in turn is dependent on their physical design, aka morphology. However, with the exception of a few (albeit ad hoc) evolutionary robotics methods, there has been very little work on understanding the interplay of morphology and collective behavior. There is especially a lack of computational frameworks to concurrently search for the robot morphology and the hyper-parameters of their behavior model that jointly optimize the collective (team) performance. To address this gap, this paper proposes a new co-design framework. Here the exploding computational cost of an otherwise nested morphology/behavior co-design is effectively alleviated through the novel concept of “talent” metrics; while also allowing significantly better solutions compared to the typically sub-optimal sequential morphology → behavior design approach. This framework comprises four major steps: talent metrics selection, talent Pareto exploration (a multi-objective morphology optimization process), behavior optimization, and morphology finalization. This co-design concept is demonstrated by applying it to design UAVs that operate as a team to localize signal sources, e.g., in victim search and hazard localization. Here, the collective behavior is driven by a recently reported batch Bayesian search algorithm called Bayes-Swarm. Our case studies show that the outcome of co-design provides significantly higher success rates in signal source localization compared to a baseline design, across a variety of signal environments and teams with 6 to 15 UAVs. Moreover, this co-design process provides two orders of magnitude reduction in computing time compared to a projected nested design approach.  more » « less
Award ID(s):
2048020
NSF-PAR ID:
10345373
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Page Range / eLocation ID:
388 to 393
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ( , Journal of Computing and Information Science in Engineering)
    null (Ed.)
    Abstract Swarm robotic search aims at searching targets using a large number of collaborating simple mobile robots, with applications to search and rescue and hazard localization. In this regard, decentralized swarm systems are touted for their coverage scalability, time efficiency, and fault tolerance. To guide the behavior of such swarm systems, two broad classes of approaches are available, namely, nature-inspired swarm heuristics and multi-robotic search methods. However, the ability to simultaneously achieve efficient scalability and provide fundamental insights into the exhibited behavior (as opposed to exhibiting a black-box behavior) remains an open problem. To address this problem, this paper extends the underlying search approach in batch-Bayesian optimization to perform search with embodied swarm agents operating in a (simulated) physical 2D arena. Key contributions lie in (1) designing an acquisition function that not only balances exploration and exploitation across the swarm but also allows modeling knowledge extraction over trajectories and (2) developing its distributed implementation to allow asynchronous task inference and path planning by the swarm robots. The resulting collective informative path planning approach is tested on target-search case studies of varying complexity, where the target produces a spatially varying (measurable) signal. Notably, superior performance, in terms of mission completion efficiency, is observed compared to exhaustive search and random walk baselines as well as a swarm optimization-based state-of-the-art method. Favorable scalability characteristics are also demonstrated. 
    more » « less
  2. ; ; ; ; ( , Structural and Multidisciplinary Optimization)
    Abstract

    To solve complex real-world problems, heuristics and concept-based approaches can be used to incorporate information into the problem. In this study, a concept-based approach called variable functioning (Fx) is introduced to reduce the optimization variables and narrow down the search space. In this method, the relationships among one or more subsets of variables are defined with functions using information prior to optimization; thus, the function variables are optimized instead of modifying the variables in the search process. By using the problem structure analysis technique and engineering expert knowledge, theFxmethod is used to enhance the steel frame design optimization process as a complex real-world problem. Herein, the proposed approach was coupled with particle swarm optimization and differential evolution algorithms then applied for three case studies. The algorithms are applied to optimize the case studies by considering the relationships among column cross-section areas. The results show thatFxcan significantly improve both the convergence rate and the final design of a frame structure, even if it is only used for seeding.

     
    more » « less
  3. ; ; ( , Model-Driven Requirements Engineering)
    null (Ed.)
    The use of semi-autonomous Unmanned Aerial Vehicles (UAVs or drones) to support emergency response scenarios, such as fire surveillance and search-and-rescue, has the potential for huge societal benefits. Onboard sensors and artificial intelligence (AI) allow these UAVs to operate autonomously in the environment. However, human intelligence and domain expertise are crucial in planning and guiding UAVs to accomplish the mission. Therefore, humans and multiple UAVs need to collaborate as a team to conduct a time-critical mission successfully. We propose a meta-model to describe interactions among the human operators and the autonomous swarm of UAVs. The meta-model also provides a language to describe the roles of UAVs and humans and the autonomous decisions. We complement the meta-model with a template of requirements elicitation questions to derive models for specific missions. We also identify common scenarios where humans should collaborate with UAVs to augment the autonomy of the UAVs. We introduce the meta-model and the requirements elicitation process with examples drawn from a search-and-rescue mission in which multiple UAVs collaborate with humans to respond to the emergency. We then apply it to a second scenario in which UAVs support first responders in fighting a structural fire. Our results show that the meta-model and the template of questions support the modeling of the human-on-the-loop human interactions for these complex missions, suggesting that it is a useful tool for modeling the human-on-the-loop interactions for multi-UAVs missions. 
    more » « less
  4. ; ; ; ; ( , Proceedings of the ASME 2022 Conference on Smart Materials, Adaptive Structures and Intelligent Systems. ASME 2022 Conference on Smart Materials, Adaptive Structures and Intelligent Systems. Dearborn, Michigan, USA. September 12–14, 2022. V001T02A008. ASME.)
    Abstract

    Additive manufacturing, no longer reserved exclusively for prototyping components, can create parts with complex geometries and locally tailored properties. For example, multiple homogenous material sources can be used in different regions of a print or be mixed during printing to define properties locally. Additionally, heterogeneous composites provide an opportunity for another level of tuning properties through processing. For example, within particulate-filled polymer matrix composites before curing, the presence of an applied electric and/or magnetic fields can reorient filler particles and form hierarchical structures depending on the fields applied. Control of particle organization is important because effective material properties are highly dependent on the distribution of filler material within composites once cured. While previous work in homogenization and effective medium theories have determined properties based upon ideal analytic distributions of particle orientations and spatial location, this work expands upon these methods generating discrete distributions from quasi-Monte Carlo simulations of the electromagnetic processing event. Results of simulations provide predicted microarchitectures from which effective properties are determined via computational homogenization.

    These particle dynamics simulations account for dielectric and magnetic forces and torques in addition to hydrodynamic forces and hard particle separation. As such, the distributions generated are processing field dependent. The effective properties for a composite represented by this distribution are determined via computational homogenization using finite element analysis (FEA). This provides a path from constituents, through processing parameters to effective material properties. In this work, we use these simulations in conjunction with a multi-objective optimization scheme to resolve the relationships between processing conditions and effective properties, to inform field-assisted additive manufacturing processes.

    The constituent set providing the largest range of properties can be found using optimization techniques applied to the aforementioned simulation framework. This key information provides a recipe for tailoring properties for additive manufacturing design and production. For example, our simulation results show that stiffness for a 10% filler volume fraction can increase by 34% when aligned by an electric field as compared to a randomly distributed composite. The stiffness of this aligned sample is also 29% higher in the direction of the alignment than perpendicular to it, which only differs by 5% from the random case [1]. Understanding this behavior and accurately predicting composite properties is key to producing field processed composites and prints. Material property predictions compare favorably to effective medium theory and experimentation with trends in elastic and magnetic effective properties demonstrating the same anisotropic behavior as a result of applied field processing. This work will address the high computational expense of physics simulation based objective functions by using efficient algorithms and data structures. We will present an optimization framework using nested gradient searches for micro barium hexaferrite particles in a PDMS matrix, optimizing on composite magnetization to determine the volume fraction of filler that will provide the largest range of properties by varying the applied electric and magnetic fields.

     
    more » « less
  5. ; ; ; ; ; ; ( , 2022 IEEE International Symposium on High-Performance Computer Architecture (HPCA))
    Quantum noise is the key challenge in Noisy Intermediate-Scale Quantum (NISQ) computers. Previous work for mitigating noise has primarily focused on gate-level or pulse-level noise-adaptive compilation. However, limited research has explored a higher level of optimization by making the quantum circuits themselves resilient to noise.In this paper, we propose QuantumNAS, a comprehensive framework for noise-adaptive co-search of the variational circuit and qubit mapping. Variational quantum circuits are a promising approach for constructing quantum neural networks for machine learning and variational ansatzes for quantum simulation. However, finding the best variational circuit and its optimal parameters is challenging due to the large design space and parameter training cost. We propose to decouple the circuit search from parameter training by introducing a novel SuperCircuit. The SuperCircuit is constructed with multiple layers of pre-defined parameterized gates (e.g., U3 and CU3) and trained by iteratively sampling and updating the parameter subsets (SubCircuits) of it. It provides an accurate estimation of SubCircuits performance trained from scratch. Then we perform an evolutionary co-search of SubCircuit and its qubit mapping. The SubCircuit performance is estimated with parameters inherited from SuperCircuit and simulated with real device noise models. Finally, we perform iterative gate pruning and finetuning to remove redundant gates in a fine-grained manner.Extensively evaluated with 12 quantum machine learning (QML) and variational quantum eigensolver (VQE) benchmarks on 14 quantum computers, QuantumNAS significantly outperforms noise-unaware search, human, random, and existing noise-adaptive qubit mapping baselines. For QML tasks, QuantumNAS is the first to demonstrate over 95% 2-class, 85% 4-class, and 32% 10-class classification accuracy on real quantum computers. It also achieves the lowest eigenvalue for VQE tasks on H 2 , H 2 O, LiH, CH 4 , BeH 2 compared with UCCSD baselines. We also open-source the TorchQuantum library for fast training of parameterized quantum circuits to facilitate future research. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email