Autonomous Parking Strategy

Author(s):  
Nikolai Moshchuk ◽  
Shih-Ken Chen

Parallel parking can be a difficult task for novice drivers or drivers who seldom drive in congested city where parking space is limited. Parking Assist is an innovative system designed to aid the driver in performing sometimes difficult parallel parking maneuvers. Many companies are developing such systems with major automakers, such as Valeo, Aisin Seiki, Hella, Robert Bosch, and TRW. For example, Toyota IPA (Intelligent Parking Assist) system uses a rear view camera and automatically steer the vehicle into the parking spot with driver controlling braking. This paper describes the development of parking path planning strategies based on available parking space. A virtual turn center will first be defined and derived based on vehicle configuration. Required parking space for one or two cycle parking maneuver will then be determined. Path planning strategies for both one and two turn parking maneuvers will be developed next. Finally CarSim simulation will be performed to verify the design.

Author(s):  
Edward Reutzel ◽  
Kevin Gombotz ◽  
Richard Martukanitz ◽  
Panagiotis Michaleris

2022 ◽  
pp. 1-13
Author(s):  
Ifat Jahangir ◽  
Darun Barazanchy ◽  
Floris-Jan van Zanten ◽  
Michel van Tooren

2018 ◽  
Vol 181 ◽  
pp. 06007
Author(s):  
Rudy Setiawan

The study reports the effect of additional parking space for the tandem parking upstream stall and downstream stall to reduce parking maneuver time compare with conventional parallel parking maneuver time. The experiments involving 295 students of Petra Christian University. Results indicate that, added one-meter additional parking space could reduce total maneuver time up to 29% for the upstream stall and 31% for the downstream stall, and also reduce 8% income from on-street parking fee, but also will reduce 35% loss due to the delay time caused by parallel parking maneuver.


10.5772/5787 ◽  
2005 ◽  
Vol 2 (3) ◽  
pp. 21
Author(s):  
Kristo Heero ◽  
Alvo Aabloo ◽  
Maarja Kruusmaa

This paper examines path planning strategies in partially unknown dynamic environemnts and introduces an approach to learning innovative routes. The approach is verified against shortest path planning with a distance transform algorithm, local and global replanning and suboptimal route following in unknown, partially unknown, static and dynamic environments. We show that the learned routes are more reliable and when traversed repeatedly the robot's behaviour becomes more predictable. The test results also suggest that the robot's behaviour depends on knowledge about the environemnt but not about the path planning strategy used.


1992 ◽  
Vol 23 (1-4) ◽  
pp. 15-18 ◽  
Author(s):  
Vivek Narayanan ◽  
Bopaya Bidanda ◽  
Jacob Rubinovitz

Sign in / Sign up

Export Citation Format

Share Document