Supermarkets need to implement safety measures to create a safe environment for shoppers and employees. Many of these injuries, such as falls, are caused by a lack of safety precautions. Such incidents are preventable by timely detection of hazardous conditions such as undesirable objects on supermarket floors. In this paper, we describe EdgeLite, a new lightweight deep learning model specifically designed for local and fast inference on edge devices which have limited memory and compute power. We show how EdgeLite was deployed on three different edge devices for detecting hazards in images of supermarket floors. On our dataset of supermarket floor hazards, EdgeLite outperformed six state-of-the-art object detection models in terms of accuracy when deployed on the three small devices. Our experiments also showed that energy consumption, memory usage, and inference time of EdgeLite were comparable to that of the baseline models. Based on our experiments, we provide recommendations to practitioners for overcoming resource limitations and execution bottlenecks when deploying deep learning models in settings involving resource-constrained hardware.

A technique for approximating a continuous function of n variables with a radial basis function (RBF) neural network is presented. The method uses an n-dimensional raised-cosine type of RBF that is smooth, yet has compact support. The RBF network coefficients are low-order polynomial functions of the input. A simple computational procedure is presented which significantly reduces the network training and evaluation time. Storage space is also reduced by allowing for a nonuniform grid of points about which the RBFs are centered. The network output is shown to be continuous and have a continuous first derivative. When the network is used to approximate a nonlinear dynamic system, the resulting system is bounded-input bounded-output stable. For the special case of a linear system, the RBF network representation is exact on the domain over which it is defined, and it is optimal in terms of the number of distinct storage parameters required. Several examples are presented which illustrate the effectiveness of this technique.

Two robust controllers are developed for the position and force control of a single n-joint nonredundant manipulator. The control strategies are shown to apply when the manipulator is unconstrained and when it is constrained by a rigid environment. Starting with the model of the robot dynamics and constraints in joint space, a dynamic equation is developed with respect to a set of task space coordinate variables. Using this task space model, the two control strategies are developed for the manipulator, and are shown to be robust with respect to uncertainty in the system. The robust control strategies have the following characteristics: (1) exponential convergence for motion tracking, (2) the controller is continuous for all times of interest, and (3) the controller is the same for constrained and unconstrained motion.>