Visual Navigation Based on Semantic Segmentation Using Only a Monocular Camera as an External Sensor

The most popular external sensor for robots capable of autonomous movement is 3D LiDAR. However, cameras are typically installed on robots that operate in environments where humans live their daily lives to obtain the same information that is presented to humans, even though autonomous movement itself can be performed using only 3D LiDAR. The number of studies on autonomous movement for robots using only visual sensors is relatively small, but this type of approach is effective at reducing the cost of sensing devices per robot. To reduce the number of external sensors required for autonomous movement, this paper proposes a novel visual navigation scheme using only a monocular camera as an external sensor. The key concept of the proposed scheme is to select a target point in an input image toward which a robot can move based on the results of semantic segmentation, where road following and obstacle avoidance are performed simultaneously. Additionally, a novel scheme called virtual LiDAR is proposed based on the results of semantic segmentation to estimate the orientation of a robot relative to the current path in a traversable area. Experiments conducted during the course of the Tsukuba Challenge 2019 demonstrated that a robot can operate in a real environment containing several obstacles, such as humans and other robots, if correct results of semantic segmentation are provided.

Vehicle speed preview control with road curvature information for safety and comfort promotion

Vehicle lateral acceleration is a critical state and index for vehicle safety and ride comfort. To limit it in high speed cornering situation, a vehicle speed preview controller is proposed with the information of future road curvature, just as a human driver behavior. The future road curvature can be obtained from high definition map in intelligent vehicle control, and to implement it, model predictive control method (MPC) is implemented taking advantage of its preview nature. In this preview speed control framework, a novel kinematics model with vehicle location, speed and track curvature is established for vehicle states prediction. The control performance index of MPC is constructed with vehicle road following index and lateral acceleration index with the aiming of promoting safety and ride comfort. The controller is evaluated during cornering with different road trajectory, initial speed, preview time and road adhesion coefficient in a hardware-in-the-loop simulation platform. It is testified that vehicle slows down before cornering as human driver does to decrease lateral acceleration and steering angle with the benefit of promoting comfort and safety.

Introduction

After establishing the scope and critical context of the book, the Introduction gives a brief history of the A591 main road linking Kendal and Keswick. This ancient road was and is the central axis of the Lake District in many respects; it was a setting for several poems of Wordsworth, and along it Wordsworth, Coleridge and other Romantic writers took up residence. Attracted by these literary associations and by the spectacular landscape, tourists have journeyed along the road on foot, by coach, by bicycle, and in motor vehicles. The surrounding landscape has also been a centre of campaigns against many projected incursions by railways and road constructions. As a principal site of the book, this chapter gives a cultural and social portrayal of the road, following Hardwick Drummond Rawnsley’s coach journey of 1888 — a glimpse of the last days of pre-modern literary tourism by coach — to highlight how this traditional mode of travel was affected by the age of transport revolutions.