Lightweight Depth Completion Network with Local Similarity-Preserving Knowledge Distillation.

Depth perception capability is one of the essential requirements for various autonomous driving platforms. However, accurate depth estimation in a real-world setting is still a challenging problem due to high computational costs. In this paper, we propose a lightweight depth completion network for depth perception in real-world environments. To effectively transfer a teacher's knowledge, useful for the depth completion, we introduce local similarity-preserving knowledge distillation (LSPKD), which allows similarities between local neighbors to be transferred during the distillation. With our LSPKD, a lightweight student network is precisely guided by a heavy teacher network, regardless of the density of the ground-truth data. Experimental results demonstrate that our method is effective to reduce computational costs during both training and inference stages while achieving superior performance over other lightweight networks.

Lane Detection Aided Online Dead Reckoning for GNSS Denied Environments.

With the emerging interest of autonomous vehicles (AV), the performance and reliability of the land vehicle navigation are also becoming important. Generally, the navigation system for passenger car has been heavily relied on the existing Global Navigation Satellite System (GNSS) in recent decades. However, there are many cases in real world driving where the satellite signals are challenged; for example, urban streets with buildings, tunnels, or even underpasses. In this paper, we propose a novel method for simultaneous vehicle dead reckoning, based on the lane detection model in GNSS-denied situations. The proposed method fuses the Inertial Navigation System (INS) with learning-based lane detection model to estimate the global position of vehicle, and effectively bounds the error drift compared to standalone INS. The integration of INS and lane model is accomplished by UKF to minimize linearization errors and computing time. The proposed method is evaluated through the real-vehicle experiments on highway driving, and the comparative discussions for other dead-reckoning algorithms with the same system configuration are presented.

Design and Performance Evaluation of an Electro-Hydraulic Camless Engine Valve Actuator for Future Vehicle Applications.

This paper details the new design and dynamic simulation of an electro-hydraulic camless engine valve actuator (EH-CEVA) and experimental verification with lift position sensors. In general, camless engine technologies have been known for improving fuel efficiency, enhancing power output, and reducing emissions of internal combustion engines. Electro-hydraulic valve actuators are used to eliminate the camshaft of an existing internal combustion engines and used to control the valve timing and valve duration independently. This paper presents novel electro-hydraulic actuator design, dynamic simulations, and analysis based on design specifications required to satisfy the operation performances. An EH-CEVA has initially been designed and modeled by means of a powerful hydraulic simulation software, AMESim, which is useful for the dynamic simulations and analysis of hydraulic systems. Fundamental functions and performances of the EH-CEVA have been validated through comparisons with experimental results obtained in a prototype test bench.