| 1. |
- Benderius, Ola, 1985, et al.
(författare)
-
Are we ready for beyond-application high-volume data? The Reeds robot perception benchmark dataset
- 2021
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- This paper presents a dataset, called Reeds, for research on robot perception algorithms. The dataset aims to provide demanding benchmark opportunities for algorithms, rather than providing an environment for testing application-specific solutions. A boat was selected as a logging platform in order to provide highly dynamic kinematics. The sensor package includes six high-performance vision sensors, two long-range lidars, radar, as well as GNSS and an IMU. The spatiotemporal resolution of sensors were maximized in order to provide large variations and flexibility in the data, offering evaluation at a large number of different resolution presets based on the resolution found in other datasets. Reeds also provides means of a fair and reproducible comparison of algorithms, by running all evaluations on a common server backend. As the dataset contains massive-scale data, the evaluation principle also serves as a way to avoid moving data unnecessarily. It was also found that naive evaluation of algorithms, where each evaluation is computed sequentially, was not practical as the fetch and decode task of each frame would not scale well. Instead, each frame is only decoded once and then fed to all algorithms in parallel, including for GPU-based algorithms.
|
|
| 2. |
- Blanch, Krister, 1991
(författare)
-
Beyond-application datasets and automated fair benchmarking
- 2023
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Beyond-application perception datasets are generalised datasets that emphasise the fundamental components of good machine perception data. When analysing the history of perception datatsets, notable trends suggest that design of the dataset typically aligns with an application goal. Instead of focusing on a specific application, beyond-application datasets instead look at capturing high-quality, high-volume data from a highly kinematic environment, for the purpose of aiding algorithm development and testing in general. Algorithm benchmarking is a cornerstone of autonomous systems development, and allows developers to demonstrate their results in a comparative manner. However, most benchmarking systems allow developers to use their own hardware or select favourable data. There is also little focus on run time performance and consistency, with benchmarking systems instead showcasing algorithm accuracy. By combining both beyond-application dataset generation and methods for fair benchmarking, there is also the dilemma of how to provide the dataset to developers for this benchmarking, as the result of a high-volume, high-quality dataset generation is a significant increase in dataset size when compared to traditional perception datasets. This thesis presents the first results of attempting the creation of such a dataset. The dataset was built using a maritime platform, selected due to the highly dynamic environment presented on water. The design and initial testing of this platform is detailed, as well as as methods of sensor validation. Continuing, the thesis then presents a method of fair benchmarking, by utilising remote containerisation in a way that allows developers to present their software to the dataset, instead of having to first locally store a copy. To test this dataset and automatic online benchmarking, a number of reference algorithms were required for initial results. Three algorithms were built, using the data from three different sensors captured on the maritime platform. Each algorithm calculates vessel odometry, and the automatic benchmarking system was utilised to show the accuracy and run-time performance of these algorithms. It was found that the containerised approach alleviated data management concerns, prevented inflated accuracy results, and demonstrated precisely how computationally intensive each algorithm was.
|
|
| 3. |
- Engström, Artur, et al.
(författare)
-
A lidar-only SLAM algorithm for marine vessels and autonomous surface vehicles
- 2022
-
Ingår i: IFAC-PapersOnLine. - : Elsevier BV. - 2405-8963. ; 55:31, s. 229-234
-
Konferensbidrag (refereegranskat)abstract
- Research into autonomous surface vehicles is noticeably limited in regards to the functionality of the vehicles themselves. Specifically, testing and evaluation typically occurs at speeds considerably lower than what is allowed in an operational setting. For a vessel to be able to take advantage of higher speeds, there must be a robust and tested method for determining localisation and navigation. With an emphasis of development for small vessels with higher impulse capabilities, working in confined and restricted environments, the decision was made to develop a method of navigation that relied solely upon lightweight sensors. For this, a single light ranging sensor was utilised to develop both simultaneous localisation and mapping for the vessel, using the normal distribution transform and iterative closest point methods. Evaluation of the algorithm accuracy as the vessel moved above speeds greater than two metres per second was conducted, and it was feasibly evaluated that there was no observable drift of mapping in horizontal planes, however, there was a accumulated drift in the vertical plane and a transient response in localisation deviation as the vessel changed impulse through the two metre per second window.
|
|
| 4. |
- Nguyen, Björnborg, 1992, et al.
(författare)
-
Application and evaluation of direct sparse visual odometry in marine vessels
- 2022
-
Ingår i: IFAC-PapersOnLine. - : Elsevier BV. - 2405-8963. ; 55:31, s. 235-242
-
Konferensbidrag (refereegranskat)abstract
- With the international community pushing for a computer vision based option to the laws requiring a look-out for marine vehicles, there is now a significant motivation to provide digital solutions for navigation using these envisioned mandatory visual sensors. This paper explores the monocular direct sparse odometry algorithm when applied to a typical marine environment. The method uses a single camera to estimate a vessel's motion and position over time and is then compared to ground truth to establish feasibility as both a local and global navigation system. Whilst it was inconsistent in accurately estimating vessel position, it was found that it could consistently estimate the vessel's orientation in the majority of the situations the vessel was tasked with. It is therefore shown that monocular direct sparse odometry is partially suitable as a standalone navigation system and is a strong base for a multi-sensor solution.
|
|
