Cooperative perception, or collective perception (CP), is an emerging and promising technology for intelligent transportation systems (ITS). It enables an ITS station (ITS-S) to share its local perception information with others by means of vehicle-to-X (V2X) communication, thereby achieving improved efficiency and safety in road transportation. In this paper, we present our recent progress on the development of a connected and automated vehicle (CAV) and intelligent roadside unit (IRSU). The main contribution of the work lies in investigating and demonstrating the use of CP service within intelligent infrastructure to improve awareness of vulnerable road users (VRU) and thus safety for CAVs in various traffic scenarios. We demonstrate in experiments that a connected vehicle (CV) can “see” a pedestrian around the corners. More importantly, we demonstrate how CAVs can autonomously and safely interact with walking and running pedestrians, relying only on the CP information from the IRSU through vehicle-to-infrastructure (V2I) communication. This is one of the first demonstrations of urban vehicle automation using only CP information. We also address in the paper the handling of collective perception messages (CPMs) received from the IRSU, and passing them through a pipeline of CP information coordinate transformation with uncertainty, multiple road user tracking, and eventually path planning/decision-making within the CAV. The experimental results were obtained with manually driven CV, fully autonomous CAV, and an IRSU retrofitted with vision and laser sensors and a road user tracking system.

The concept of Smart Grids is closely related to energy conservation and load shedding concepts. However, it is difficult to quantify the effectiveness of energy conservation efforts in residential settings without any sort of end-use energy information as feedback. In order to achieve that, load monitoring methods are normally used. In recent years, non-intrusive load monitoring (NILM) approaches are gaining popularity due to their minimal installation requirements and cost effectiveness. For a NILM system to work, only one sensor at the entry point to a home is required. Fluctuations in the aggregate power consumption signals are used to mathematically estimate the composition of operation of appliances. This approach eliminates the requirement of installing plug-meters for every appliance in the house. In this paper, we provide a review of recent research efforts on state-of-the-art NILM algorithms before concluding with a baseline and overall vision for our future research direction.

A new particle‐based distribution truncation method with a duration‐dependent hidden semi‐Markov model for non‐intrusive appliance load monitoring is presented. Unlike earlier works, the approach keeps track of a set of states without prematurely pruning away intermediately ranked states. It also enables appliance state duration characteristics to be incorporated in a straightforward manner. Results show that the approach outperforms both the Viterbi algorithm and conventional particle‐filtering methods.

Non-intrusive Load Monitoring (NILM) is a hallmark of monitoring technologies. It provides appliance-level energy usage feedback with minimal sensor deployments. How-ever, existing NILM systems are not designed with embedded systems (e.g. Smart Meters) in mind. In this paper, we consider a Bayesian solution which efficiently computes the Log-Likelihood Ratio (LLR) of an appliance's on/off state, then combines it with historical estimates to yield a new estimate for improved accuracy. The detection of multiple appliances is achieved through an iterative method which also deals with unidentified appliances. With minimal multiplication and division, the algorithm is computationally lightweight and can easily be implemented in embedded systems using low-power processors. Despite the simplicity, results show promising disaggregation performance.

This paper assesses the performance of a technique for estimating the power consumption of individual devices based on aggregate consumption. The new semi-Markov technique, outperforms pure hidden Markov models on the REDD dataset. The technique also exploits information from transients to eliminate a substantial fraction of the observed errors.