CEVA Announces SLAM SDK for Low-Power Embedded Systems
Published2019.06.05 12:13CEVA today announced the CEVA-SLAM Software Development Kit (SDK) to simplify the development of Simultaneous Localization and Mapping (SLAM) for mobile, AR/VR headsets, robots, autonomous vehicles and camera-based devices.
Available for the CEVA-XM intelligent vision DSPs and NeuPro AI processor families, CEVA-SLAM integrates hardware, software and interfaces to significantly lower the barrier to entry for companies looking to implement SLAM in low-power embedded systems.
The CEVA-SLAM SDK accelerates the development of SLAM-based applications by integrating the hardware, software and interfaces for efficient SLAM implementations that can run on embedded systems across multiple platforms, as well as includes detailed interfaces to offload the heavy lifting SLAM blocks from the CPU to the CEVA-XM DSP.
CEVA-SLAM SDK building blocks are floating point and floatingLeverage the efficiency of the DSP to fully support floating point operations to extend device battery life, allowing you to use your device for longer.
SDK building blocks include image processing functions (feature extraction, feature descriptors, feature matching), linear algebra (matrix transformations, linear equation solving), and sparse equation solving for bundle adjustment.
The low power performance of the CEVA-SLAM SDK consumes only 86mW when running a full SLAM tracking module at 60 frames per second on the CEVA-XM6 DSP.
When utilizing CEVA-XM series DSPs or NeuPro AI processors, customers can address a wide range of use cases and applications requiring SLAM.
For example, classical approaches for computer imaging and vision or visual positioning functions using neural networks can also be processed on a single, easily programmable hardware platform.
The CEVA-SLAM SDK is currently available for licensing with CEVA-XM intelligent vision DSPs and NeuPro AI processors. For more information, please visit our website .
Ilan Yona, vice president and general manager of the Vision Business Unit at CEVA, said: “SLAM is a technology that allows creating an extremely accurate 3D map of the device’s surroundings and is a key enabler for a wide range of emerging devices, including AR/VR headsets, drones, robots and other autonomous machines. CEVA has leveraged this expertise to design a vision DSP and software algorithms to enable our customers to enter the exciting, yet complex, space of 3D machine vision.”
관련뉴스
LG Electronics partners with world-class universities to offer an "AI Expert" course to enhance the expertise of its in-house AI workforce.
LG Electronics operates an education and certification program for fostering AI experts in collaboration with Carnegie Mellon University in the United States and the University of Toronto in Canada. LG Electronics selected 12 trainees from among its in-house master's and doctoral-level AI developers through technical interviews. The selected trainees will receive one-on-one instruction from faculty members at each university over the following 16 weeks while conducting individual projects in the fields of voice intelligence, video intelligence, and control intelligence. Subsequently, the project results undergo review by a certification committee including the supervising professors, and those who pass are selected as LG Electronics AI experts.
2019.04.22by 이수민 기자
SKT and Seoul Metropolitan Government Usher in the Era of Fully Autonomous Driving with 5G and AI
SK Telecom's B2B Business Division Head Choi Il-kyu and Seoul City's Urban Transportation Director Koh Hong-seok signed an agreement on technology development and demonstration for high-precision road map technology for the autonomous driving era. Both parties agreed to cooperate in developing real-time HD map update technology for the next-generation intelligent transportation system demonstration project section by equipping 5G ADAS on 1,700 city buses and taxis. Based on this, they plan to undertake road facility management system and traffic safety service development projects as well. Through this agreement, Seoul is expected to become the world's first city to apply 5G technology in the public transportation sector.
2019.05.26by 이수민 기자
The surge in IDC traffic in the 5G era… FPGAs are the answer.
The importance of data centers and the utilization rate of IoT devices have increased significantly in recent years. Consequently, the demand for FPGAs is gradually rising in various application fields that previously relied mainly on conventional processors. This is because FPGAs offer better efficiency than traditional processors for specialized purposes. Agilex, the first FPGA released by Intel following its acquisition of Altera, has drawn attention as a semiconductor manufactured using Intel's 10nm process. An even more interesting aspect is that it supports CXL specifications, a recently disclosed next-generation interface standard, as well as PCIe 5.0. Agilex can secure sufficient bandwidth even when used alongside dedicated accelerators such as CPUs and GPUs. Moreover, it not only supports ultra-high-speed memory such as DDR5 and HBM2, but also supports Intel Optane DC Persistent Memory.
2019.06.03by 이수민 기자
ST Microelectronics and NUS Establish Joint Research Center 'HELIX' for Edge AI
ST Microelectronics and the National University of Singapore have established the 'HELIX' joint research center aimed at implementing embedded AI in edge environments. Over a four-year period, the center will conduct research across the entire technology stack from algorithms to silicon, focusing on memory-centric architecture leveraging ST's 18nm FD-SOI technology and embedded PCM. The core objective is to implement intelligence directly in physical devices such as robots and drones while minimizing energy consumption.
2026.08.28by 배종인 기자
ams, 디지털 포토닉스로 휴머노이드 로봇 감각·소통 기능 지원
ams OSRAM이 디지털 포토닉스 기술을 활용해 휴머노이드 로봇의 감각·소통 기능을 강화하는 솔루션을 공개했다. dToF 센서, 광학식 힘 센서, 구조광 이미터 등으로 주변 환경 인식과 정밀 조작을 구현하며, EVIYOS·ALIYOS 플랫폼으로 LED 기반 비언어 소통을 지원한다. 시장조사에 따르면 휴머노이드 로봇 시장은 2025년 6억 달러에서 2035년 510억 달러로 성장할 전망이며, 로봇의 감각 능력 향상이 핵심 성장 동인으로 작용할 것으로 예상된다.
2026.08.27by 배종인 기자
