A Universal LiDAR SLAM Accelerator System on Low-Cost FPGA

Sugiura, Keisuke; Matsutani, Hiroki

doi:10.1109/access.2022.3157822

Cited by 19 publications

(15 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Laser SLAM uses LiDAR to sense the environment and generate high-accuracy and reliable maps [23][24][25][26][27][28]. It has widespread use in areas such as unmanned vehicles, drones, and indoor mobile robots.…”

Section: Related Workmentioning

confidence: 99%

Field Robot Self-Exploration Based on Deep Reinforcement Learning and Safety Control Mechanism

Kang,

Zhang,

et al. 2024

Preprint

View full text Add to dashboard Cite

This paper aims to address the issues that arise when using deep reinforcement learning algorithms for reactive robotic navigation in farmland environments. These challenges include complex network models, a large number of parameters, significant computational requirements, and the possibility of being vulnerable to local optimal solutions. Moreover, the complexity of the farmland environment poses a challenge to the existing indoor reactive navigation methods, which struggle to meet the requirements of tasks such as crop protection and human cooperation.To address these issues, the paper proposes the Field Robot Autonomous Navigation System (FRANS), which utilizes Deep Reinforcement Learning (DRL) to enable farmland robots to autonomously explore unknown environments. The system consists of two modules: Global Navigation (GN) and Local Navigation (LN). The GN module establishes goal points and implements a secure control mechanism to manage the robot's actions. This approach helps to address problems like locally optimal solutions. The LN module uses a lightweight DRL framework to develop a locally navigated motion strategy that guides the robot toward waypoints. FRANS does not require any prior knowledge and is capable of adjusting the navigation strategy in real time based on the current environment. The map is generated in real time as the robot moves through the environment. Experimental results demonstrate that FRANS outperforms similar approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

Field Robot Self-Exploration Based on Deep Reinforcement Learning and Safety Control Mechanism

Kang,

Zhang,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Other advances toward VO/SLAM acceleration include LiDAR SLAM accelerators in [36], [37], and [38], as well as accelerators for Iterative Closest Point (ICP) ( [34] and [35]).…”

Section: ) Accelerating Vo/slam Systems On Fpgasmentioning

confidence: 99%

“…Sugiura and Matsutani [36] have proposed a universal, low-power, and resource-efficient accelerator design for 2D LiDAR SLAM targeting resource-limited FPGAs. They accelerated scan matching, which is the core for LiDAR-based SLAM on FPGA.…”

Section: ) Accelerating Vo/slam Systems On Fpgasmentioning

confidence: 99%

Exploring Sparse Visual Odometry Acceleration With High-Level Synthesis

Iordanou

Riley

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Visual Odometry (VO) systems are widely used to determine the position and orientation of a robot or camera in an unknown environment. They are deployed on resource-constrained platforms, such as drones and Virtual Reality (VR) or Augmented Reality (AR) headsets. VO systems harnessing modern System-on-Chip (SoCs) with integrated Field Programmable Gate Array (FPGA) have the potential to improve the overall systems performance. This paper explores the FPGA acceleration of sparse VO kernels using High-level Synthesis (HLS) as this kind of VO system has been designed to use with lowpower SoCs. We show that both computational and data transfer overheads between the processing cores of the CPU of the SoC and the accelerators on the FPGA need to be optimized to obtain better end-to-end performance. This is a result of the additional data movement incurred when using an FPGA accelerator and also because of the sparse computational nature with predictable or random memory access patterns of the kernels involved. However, state-of-the-art HLS tools are not yet able to perform the required optimizations automatically because they usually assume that the kernels to be accelerated have dense computational patterns with regular memory access. In this paper we propose three, potentially generic, methods to reduce the data transfer between the CPU and the customised hardware kernels on the FPGA; these methods are: (a) approximation based on domain-specific knowledge, (b) image compression, and (c) the use of on-the-fly computation. We present a case study of the use of these methods on SVO, a state-of-the-art sparse VO system with a semi-direct front-end. We demonstrate that our proposed methods can reduce data transfer overhead to achieve better end-to-end performance and that they can be applied not only when using standard Xilinx HLS tools but also with other state-of-the-art HLS tools, such as HeteroFlow. Compared to the baseline performance of the original SVO software on an Arm CPU, our proposed methods assist the HLS and HeteroFlow designs to achieve a speedup of 2.4x and 2.14x, respectively, without noticeable accuracy loss. The HLS and HeteroFlow designs also achieve a 1.85x and 1.89x, respectively, improvement in energy efficiency on the SoC system used. Compared to the SVO software baseline running on the Intel Xeon CPU, our proposed methods assist the HLS and HeteroFlow designs to achieve 8.2x and 8.3x improvement in energy efficiency, respectively.

show abstract

“…In this paper, a range ambiguity classification algorithm based on a single-wavelength pulsed laser and accelerated by an FPGA platform is proposed for the first time in the field of automotive LiDAR [17][18][19]. This method can accomplish the solution of the range ambiguity problem by encoding the trigger signal with a pulsed laser.…”

Section: Figurementioning

confidence: 99%

A range ambiguity classification algorithm for automotive LiDAR based on FPGA platform acceleration

Li,

Xiang,

Zhang

et al. 2023

Front. Phys.

View full text Add to dashboard Cite

In the past decade, the automotive light detection and ranging (LiDAR) has been experiencing a rapid expansion stage. Many researchers have been involved in the research of LiDARs and have installed it in vehicles as a means of enhancing autopilot capabilities. Compared with a traditional millimeter wave radar, LiDARs have many advantages such as the high imaging resolution, long measurement range, and the ability to reconstruct 3D information around the vehicle. These features make LiDARs one of the crucial research hotspots in the field of autopilot. The basic principles of LiDARs are the same as those of a laser rangefinder. The distance information can be obtained by locating the echo instant corresponding to the laser emission moment. But if the interval between two adjacent laser pulses is extremely narrow, the regions of the light emission and echo will be overlapped. Therefore, a range ambiguity will occur and the distance information calculation process will become abnormal. Besides, the high resolution of LiDARs is also characterized by its extremely high emissions frequency. Whilst the information about the surrounding environment of an automotive car can be retrieved more accurately, it means that the possibility of range ambiguity is also increasing at the same time. In this paper, we propose an algorithm for solving the range ambiguity problem of the LiDARs based on the concept of classification and can be accelerated by the FPGA approach, for the first time in the field of an automotive LiDAR. The algorithm can be performed by employing a single wavelength pulsed laser and can be specifically optimized for the demands of field programmable gate arrays (FPGAs). While guaranteeing the high resolution of LiDARs, the attenuation of the measurement ability should exceed due to the occurrence of range ambiguity. It can also match the demand for the processing speed of large amounts of point cloud information data. Through controlling the cost of the whole device, the performance of the LiDAR can be greatly improved. The result of this paper might provide a bright future of automotive LiDARs with the high data processing efficiency and the high resolution at the same time.

show abstract

A Universal LiDAR SLAM Accelerator System on Low-Cost FPGA

Cited by 19 publications

References 65 publications

Field Robot Self-Exploration Based on Deep Reinforcement Learning and Safety Control Mechanism

Field Robot Self-Exploration Based on Deep Reinforcement Learning and Safety Control Mechanism

Exploring Sparse Visual Odometry Acceleration With High-Level Synthesis

A range ambiguity classification algorithm for automotive LiDAR based on FPGA platform acceleration

Contact Info

Product

Resources

About