In our experience, the task of optimizing robot longevity and efficiency is challenging due to the limited understanding and awareness developers' have about how their code influences a robot's expected lifesp...
详细信息
In our experience, the task of optimizing robot longevity and efficiency is challenging due to the limited understanding and awareness developers' have about how their code influences a robot's expected lifespan. Unfortunately, acquiring the necessary information for computations is a complex task, and the data needed for these calculations remains unattainable until after runtime. In software engineering, traditional Static Code Analysis (SCA) techniques are applied to address such challenges. Although effective in identifying software anomalies and inefficiencies without execution, current SCA techniques do not adequately address the unique requirements of Cyber-Physical Systems (CPSs) in robotics. In this study, we propose a novel Machine Learning (ML) approach to assess robot program lines, considering the balance between speed and lifespan. Our solution, trained on data from 1325 operational collaborative robots (cobots) from the Universal Robots (UR) e-Series, classifies program lines concerning the expected lifespan of the robot, considering program line arguments, expected resource usage, and asserted joint stress. The model achieves a worst-case accuracy of 90.43% through 10-fold cross-validation with a 50% data split. We also present a selection of programming lines illustrating various robot program cases and an example of longevity improvement. Finally, we publish a dataset containing 56405 unique program line executions, aiming to enhance the sustainability and efficiency of robotic systems and support future research.
Developing autonomous vehicles (AVs) that operate in diverse and demanding environments is a difficult challenge. Two fundamental tools that can accelerate this process are testing an AV in diverse simulated environme...
详细信息
Developing autonomous vehicles (AVs) that operate in diverse and demanding environments is a difficult challenge. Two fundamental tools that can accelerate this process are testing an AV in diverse simulated environments and identifying core system weaknesses. While most efforts focus on improving these tools for on-road AVs, this letter focuses on an analogous set of tools for off-road AVs. A method called Black-Box Adversarially Compounding Regret Through Evolution (BACRE) is proposed for identifying adversarial scenarios using an evolutionary algorithm guided by a novel regret-based metric for general navigation tasks. A black-box approach is often preferable when system complexity can be diverse, like with off-road AVs, and when whole-system testing is required. A custom simulation platform is also provided to assist with the automated testing of AVs in diverse, unstructured environments. Numerical experiments demonstrate that BACRE's evolutionary process gradually increases scenario complexity to degrade vehicle performance (an effective and explainable process that comparable methods cannot achieve). Consequently, BACRE can streamline AV development by finding weaknesses at any development stage.
Event cameras capture visual information with a high temporal resolution and a wide dynamic range. This enables capturing visual information at fine time granularities (e.g., microseconds) in rapidly changing environm...
详细信息
Event cameras capture visual information with a high temporal resolution and a wide dynamic range. This enables capturing visual information at fine time granularities (e.g., microseconds) in rapidly changing environments. This makes event cameras highly useful for high-speed robotics tasks involving rapid motion, such as high-speed perception, object tracking, and control. However, convolutional neural network inference on event camera streams cannot currently perform real-time inference at the high speeds at which event cameras operate-current CNN inference times are typically closer in order of magnitude to the frame rates of regular frame-based cameras. Real-time inference at event camera rates is necessary to fully leverage the high frequency and high temporal resolution that event cameras offer. This letter presents Ev-Conv, a new approach to enable fast inference on CNNs for inputs from event cameras. We observe that consecutive inputs to the CNN from an event camera have only small differences between them. Thus, we propose to perform inference on the difference between consecutive input tensors, or the increment. This enables a significant reduction in the number of floating-point operations required (and thus the inference latency) because increments are very sparse. We design Ev-Conv to leverage the irregular sparsity in increments from event cameras and to retain the sparsity of these increments across all layers of the network. We demonstrate a reduction in the number of floating operations required in the forward pass by up to 98%. We also demonstrate a speedup of up to 1.6xfor inference using CNNs for tasks such as depth estimation, object recognition, and optical flow estimation, with almost no loss in accuracy.
Intelligent mobile robots are critical in several scenarios. However, as their computational resources are limited, mobile robots struggle to handle several tasks concurrently while guaranteeing real timeliness. To ad...
详细信息
ISBN:
(纸本)9798350304831
Intelligent mobile robots are critical in several scenarios. However, as their computational resources are limited, mobile robots struggle to handle several tasks concurrently while guaranteeing real timeliness. To address this challenge and improve the real-timeliness of critical tasks under resource constraints, we propose a fast context-aware task handling technique. To effectively handle tasks in real-time, our proposed context-aware technique comprises three main ingredients: (i) a dynamic time-sharing mechanism, coupled with (ii) an event-driven task scheduling using reactive programming paradigm to mindfully use the limited resources;and, (iii) a lightweight virtualized execution to easily integrate functionalities and their dependencies. We showcase our technique on a Raspberry-Pi-based robot with a variety of tasks such as Simultaneous localization and mapping (SLAM), sign detection, and speech recognition with a 42% speedup in total execution time compared to the common Linux scheduler.
Developments in mobile robot navigation have enabled robots to operate in warehouses, retail stores, and on sidewalks around pedestrians. Various navigation solutions have been proposed, though few as widely adopted a...
详细信息
ISBN:
(纸本)9781728162126
Developments in mobile robot navigation have enabled robots to operate in warehouses, retail stores, and on sidewalks around pedestrians. Various navigation solutions have been proposed, though few as widely adopted as ROS (Robot Operating System) Navigation. 10 years on, it is still one of the most popular navigation solutions(1). Yet, ROS Navigation has failed to keep up with modern trends. We propose the new navigation solution, Navigation2, which builds on the successful legacy of ROS Navigation. Navigation2 uses a behavior tree for navigator task orchestration and employs new methods designed for dynamic environments applicable to a wider variety of modern sensors. It is built on top of ROS2, a secure message passing framework suitable for safety critical applications and program lifecycle management. We present experiments in a campus setting utilizing Navigation2 to operate safely alongside students over a marathon as an extension of the experiment proposed in Eppstein et al. [1]. The Navigation2 system is freely available at https://***/ros-planning/navigation2 with a rich community and instructions.
When it comes to describing robots, many roboticists choose to focus on the size, types of actuators, or other physical capabilities. As most areas of robotics deploy robots with large memory and processing power, the...
详细信息
When it comes to describing robots, many roboticists choose to focus on the size, types of actuators, or other physical capabilities. As most areas of robotics deploy robots with large memory and processing power, the question "how computational resources limit what a robot can do" is often overlooked. However, the capabilities of many miniature robots are limited by significantly less memory and processing power. At present, there is no systematic approach to comparing and quantifying the computational resources as a whole and their implications. This letter proposes computational indices that systematically quantify computational resources-individually and as a whole. Then, by comparing 31 state-of-the-art miniature robots, a computational classification ranging from non-computing to minimally-constrained robots is introduced. Finally, the implications of computational constraints on robotic software are discussed.
This letter reviews the source code published with the papers of a flagship robotics research conference, 2017 International Conference on Robotics and Automation. The aim is to investigate whether the code is actuall...
详细信息
This letter reviews the source code published with the papers of a flagship robotics research conference, 2017 International Conference on Robotics and Automation. The aim is to investigate whether the code is actually useful, i.e., can he reused by an interested reader without much effort. The interest is twofold: for one side, it makes possible to replicate and validate the results of the research;for another side, it facilitates new progress on the field, since researchers can build new systems on top of existing work. Unfortunately, reusing code is not as straightforward as it could seem, and there is a need for tools that alleviate the effort for integrating someone else's code into the own user's system. We propose the use of Docker, a Linux container technology, to turn the source code repositories into executable images, that can be run and tested locally, in an isolated environment, without the need of a costly integration with the host system.
Robot task programming often leads to inefficient plans, as opportunities for parallelization and precomputation are usually not exploited by the programmer. This inefficiency is often especially obvious in mobile man...
详细信息
Robot task programming often leads to inefficient plans, as opportunities for parallelization and precomputation are usually not exploited by the programmer. This inefficiency is often especially obvious in mobile manipulation, where path planning and pose estimation algorithms are time-consuming operations. In this letter, we introduce the concept of' resource-aware task nodes (RATNs), a powerful descriptive action model for robots. Next, we propose an algorithm that executes so-called concurrent dataflow task networks (CDTNs), robot plans consisting of RATNs. It optimizes programmed plans based on two sources of information: 1) The control flow represented in the original task plan, whose constraints are relaxed to generate opportunities for parallelization and precomputation. 2) Dependencies between actions pertaining to resources, data flows, and world model changes, the latter being equivalent to preconditions and effects. CDTNshave been integrated in our open-source task programming framework RAFCON, and we show that it leads to 11%-29% improvement in terms of execution time in two simulated mobile manipulation scenarios.
In the context of space missions and terrestrial applications, both mission goals and task implementations for autonomous robots are becoming increasingly complex. Thus, the challenge of monitoring the achievement of ...
详细信息
In the context of space missions and terrestrial applications, both mission goals and task implementations for autonomous robots are becoming increasingly complex. Thus, the challenge of monitoring the achievement of task objectives and checking the correctness of their implementation is becoming more and more difficult. To tackle these problems, we propose an unified architecture that supports different stakeholders during the different phases of the deployment: 1) the design phase;2) the runtime phase;and 3) the postmortem analysis phase. Furthermore, we implement this architecture by enhancing our task programming framework RMC advanced flow control with powerful logging, debugging, and profiling capabilities. We demonstrate the efficiency of our approach in the context of the ROBEX mission, during which the DLR Lightweight Rover Unit autonomously deployed several seismometers in an unknown rough terrain on Mt. Etna, Sicily. The analysis results for a state machine consisting of more than 1500 states and more than 1900 transitions are presented. Finally, we give a comparison between our framework and related software tools.
For smart factories in the Industry 4.0 era, edge devices can be used to run intelligent software packages (i.e., manufacturing services) to support manufacturing activities of production equipment. However, this kind...
详细信息
For smart factories in the Industry 4.0 era, edge devices can be used to run intelligent software packages (i.e., manufacturing services) to support manufacturing activities of production equipment. However, this kind of edge device may fail to provide designed functionalities in time when it encounters a sudden high-computation (SHC) job that cannot be executed by the edge device itself within a required time constraint. Thus, how to assure that an edge device can effectively execute SHC jobs so as to provide manufacturing services to equipment in time is an important and challenging issue for smart manufacturing. Exiting job-shop scheduling (JSS) methods may optimally allocate jobs for production lines but cannot directly be applied to handle the edge devices SHC jobs, which occur irregularly and are hard to specify processing time slots for JSS methods. Aimed at resolving the above-mentioned issue, this letter proposes a novel manufacturing behavior-based map-reduce-style job offloading scheme. First, a distributed job processing architecture is designed to allow distributed edge devices to collaboratively complete an SHC job to support manufacturing. Next, a map-reduce-style program structure is developed so that an SHC job can be easily divided into multiple parts that can be executed in parallel by the selected edge devices, each device processing a part. Then, a mechanism of selecting proper edge devices to complete the SHC job, considering historical manufacturing behaviors of each edge device, is proposed for achieving high offloading efficiency. Finally, we simulate a factory with 20 machines to conduct integrated tests. Testing results demonstrate the effectiveness and excellent performance of the proposed scheme.
暂无评论