Job Description
1. Participate in the research and development of core vision algorithms for humanoid robots. Utilize deep learning and machine learning technologies to design and implement high-precision, real-time vision algorithms for tasks such as localization, quality inspection, object pose estimation, and alignment during factory operations. Continuously explore cutting-edge algorithms to enhance the robot's perception capabilities;
2. Integrate visual algorithms with other core algorithms within humanoid robot systems. Optimize algorithm execution efficiency on hardware devices to enhance overall visual system stability and reliability; 3. Collect relevant visual perception data during robot operations in factory environments. Build high-quality datasets and employ techniques like data augmentation to expand data diversity; Train, tune, and evaluate models based on the dataset, continuously improving model performance to enhance the adaptability and accuracy of visual perception algorithms across various scenarios; 4. Develop algorithm design and testing plans according to practical requirements, subjecting visual algorithms to rigorous testing; promptly identify and resolve issues encountered during algorithm operation, ensuring ongoing maintenance and optimization of algorithms.
1. 參與人形機器人視覺核心演算法的研發，針對機器人在工廠執行任務過程中，如定位、質檢、物體位姿估計、對齊等，運用深度學習、機器學習等技術，設計並實現高精度、即時性強的視覺演算法，不斷探索前沿演算法以提升機器人的感知能力；
2. 將視覺演算法在人形機器人系統上與其他核心演算法進行集成，優化演算法在硬體設備上的運行效率，提升整體視覺系統的穩定性和可靠性；；
3. 收集機器人在工廠運行過程中的相關視覺感知數據，構建高質量的數據集，運用數據增強等技術擴充數據多樣性；基於數據集進行模型訓練、調優和評估，不斷改進模型性能，提高視覺感知演算法對各類場景的適應性和準確性；
4. 根據實際需求，制定演算法設計方案和測試方案，對視覺演算法進行嚴格測試；及時發現並解決演算法運行過程中出現的問題，持續維護和優化演算法；
Requirements
1. Master the theoretical foundations and algorithms of artificial intelligence, pattern recognition, deep learning, and computer vision;
2. Understand typical visual perception technologies; preference given to candidates with publications in top-tier CVR conferences such as CVPR, ICCV, ECCV, TPAMI, and TIP;
3. Proficient in C/C++ and Python programming, familiar with Linux and ROS systems;
4. Possess strong teamwork and communication skills, along with excellent learning capabilities.
1. 掌握人工智慧、模式識別、深度學習、電腦視覺理論基礎和演算法；
2. 瞭解典型的視覺感知技術，在CVPR，ICCV，ECCV，TPAMI，TIP等視覺TOP期刊會議發表論文者優先；
3. 熟悉C/C++和Python編程，熟悉Linux系統和ROS系統；
4. 具備良好的團隊協作能力和溝通能力，具備良好的學習能力。
