In this paper we explore some of the potential applications of robustness criteria for machine learning (ML) systems by way of tangible “demonstrator” scenarios. In each demonstrator, ML robustness metrics are appli...
In this paper we explore some of the potential applications of robustness criteria for machine learning (ML) systems by way of tangible “demonstrator” scenarios. In each demonstrator, ML robustness metrics are applied to real-world scenarios with military relevance, indicating how they might be used to help detect and handle possible adversarial attacks on ML systems. We conclude by sketching promising future avenues of research in order to: (1) help establish useful verification methodologies to facilitate ML robustness compliance assessment; (2) support development of ML accountability mechanisms; and (3) reliably detect, repel, and mitigate adversarial attack.
Solving the Hamilton-Jacobi-Bellman equation is important in many domains including control, robotics and economics. Especially for continuous control, solving this differential equation and its extension the Hamilton...
详细信息
Although robotics courses are well established in higher education, the courses often focus on theory and sometimes lack the systematic coverage of the techniques involved in developing, deploying, and applying softwa...
详细信息
The advent of industrial robotics and autonomous systems endow human-robot collaboration in a massive scale. However, current industrial robots are restrained in co-working with human in close proximity due to inabili...
详细信息
A key step in the development of lightweight, high performance robotic systems is the modeling and selection of permanent magnet brushless direct current (BLDC) electric motors. Typical modeling analyses are completed...
详细信息
As a basic and indispensable module, LiDAR odom-etry estimation is widely used in robotics. In recent years, learning-based modeling approaches for odometry estimation have been validated to be feasible. However, it i...
详细信息
ISBN:
(纸本)9781665481106
As a basic and indispensable module, LiDAR odom-etry estimation is widely used in robotics. In recent years, learning-based modeling approaches for odometry estimation have been validated to be feasible. However, it is necessary to consider security factors as the highest priorities when we apply the learning-based model to certain high-risk real-world scenarios, such as autonomous driving. The odometry uncertainty estimation provides more valuable information for downstream tasks, such as route planning and navigation. In this paper, we propose an end-to-end neural network (namely CertainOdom) to solve odometry and uncertainty estimation tasks by applying multi-task learning. Instead of using the manually-tuned hyper-parameters, we employ the learnable uncertainties to weigh the balance between the error of translation and orientation in the loss function. We evaluate the estimated trajectory and uncertainty on KITTI dataset. We also compare the robustness against the traditional geometry-based methods on our artificially degraded KITTI LiDAR dataset. Extensive experimental results show that our model with uncertainty weighted loss achieves competitive performance in LiDAR odometry estimation. We also explain our uncertainties qualitatively and quantitatively.
Complete compliance of soft robots is a trending research topic. One significant aspect is the control element. In the current work, a flexible electro-rheological (ER) valve development is chosen due to the advantage...
详细信息
In the field of consumer electronics, Wireless Sensor Networks (WSNs) can be used to build large-scale IoT systems and achieve intelligent data collection and processing. This paper proposes a deep neural network mode...
详细信息
In the field of consumer electronics, Wireless Sensor Networks (WSNs) can be used to build large-scale IoT systems and achieve intelligent data collection and processing. This paper proposes a deep neural network model SAE-PNN by Stacked Auto Encoder (SAE) and Probabilistic Neural Network (PNN) in a stack manner. A comprehensive training algorithm of SAE-PNN based on a group of orthogonal function bases is established by introducing a time-varying input and connection weight function, based on the conventional algorithm of unsupervised layer-by-layer initialization and gradient descent of deep neural network. Our proposed SAE-PNN model is used to predict the distance from unknown nodes to known nodes. Based on the collaborative work of nodes and network coverage, an optimal set of working nodes is established to reduce the energy loss of network nodes. A balance relationship between network coverage and energy consumption has been established to solve the problem of optimizing the balance in location coverage and the contradiction between individual nodes and the overall performance of the network. The experimental results show that the proposed method can improve the coverage of the monitored area and the perceived quality of service, and uses a distributed node synchronous scheduling mechanism to reduce the overall energy consumption of the network.
Digital human animation relies on high-quality 3D models of the human face—rigs. A face rig must be accurate and, at the same time, fast to compute. One of the most common rigging models is the blendshape model. We p...
详细信息
暂无评论