As autonomous vehicles become more common on the roads, their advancement draws on safety concerns for vulnerable road users, such as pedestrians and cyclists. This paper presents a review of recent developments in pedestrian and cyclist detection and intent estimation to increase the safety of autonomous vehicles, for both the driver and other road users. Understanding the intentions of the pedestrian/cyclist enables the self-driving vehicle to take actions to avoid incidents. To make this possible, development of methods/techniques, such as deep learning (DL), for the autonomous vehicle will be explored. For example, the development of pedestrian detection has been significantly advanced using DL approaches, such as; Fast Region-Convolutional Neural Network (R-CNN) , Faster R-CNN and Single Shot Detector (SSD). Although DL has been around for several decades, the hardware to realise the techniques have only recently become viable. Using these DL methods for pedestrian and cyclist detection and applying it for the tracking, motion modelling and pose estimation can allow for a successful and accurate method of intent estimation for the vulnerable road users. Although there has been a growth in research surrounding the study of pedestrian detection using vision-based approaches, further attention should include focus on cyclist detection. To further improve safety for these vulnerable road users (VRUs), approaches such as sensor fusion and intent estimation should be investigated.
A miniature capsule robot (capsubot) -which has no external moving parts whereas a conventional robot has legs and/or wheels -is suitable for in-vivo applications, engineering diagnosis and pipe inspection. This study addresses the trajectory-tracking problem of an underactuated planar capsubot.A combining piece-wise and behaviour-based control algorithm is proposed for trajectory tracking. The paper also proposes four motion behaviours, four switching behaviours, one stationary behaviour. A selection algorithm for behavior-based control and rules for IM motion control in all the behaviours are developed. The partial feedback linearization control is used for low-level IM motion control while the piece-wise and behaviour based control is used for the capsubot trajectory tracking control.
This paper presents a miniature hybrid capsule robot for minimally invasive in-vivo interventions such as capsule endoscopy within the GI (gastrointestinal) tract. It proposes new modes of operation for the hybrid robot namely hybrid mode and anchoring mode. The hybrid mode assists the robot to open an occlusion or to widen a narrowing. The anchoring mode enables the robot to stay in a specific place overcoming external disturbances (e.g. peristalsis) for a better and prolonged observation. The modelling of the legged, hybrid and anchoring modes are presented and analysed. Simulation results show robot propulsions in various modes. The hybrid capsule robot consisting four operating modes is more effective for the locomotion and observation within GI tract when compared to the locomotion consisting a single mean of locomotion as the hybrid robot can switch among the operating modes to suit the situation/task.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.