Robotic picking and placing played an essential role in Industrial 4.0 and have long been recognized as significant contributions to industrial processes. Various scenarios involve picking and placing parts for assembly in industrial production, such as assembling different electronic components in the manufacturing process. Those tasks require high precision to complete. However, achieving high precision in the assembly of CPUs poses a significant challenge, particularly when dealing with reflective surfaces. This paper presents a strategic system design tailored to address these challenges effectively. We focus on system device choice and optimizing the key parameters of the sensor system to strike a balance between device cost and the required precision. We use methods to construct the whole robot manipulation system, such as geometric segmentation, binocular vision with structure light projection and, based on 3D information, 6D pose estimation to construct the system. The results of our study demonstrate the practical applicability and benefits of this strategic system design in industrial settings. By meeting strict system accuracy requirements, our approach contributes to advancing industry practices and growing its impact on society.

Chinese calligraphy is a complicated art form that requires precise control of movement and brush dynamics, making it a challenging task for robotic systems. This paper presents a novel approach to enabling robotic manipulators to perform Chinese calligraphy using 3D path planning algorithms and a large language model (LLM) as input generators. The proposed framework integrates an LLM to generate textual content prompts, which are then transformed into detailed 3D Bézier curve trajectories which represent the strokes of Chinese characters. These trajectories are optimized to ensure smooth and accurate motion of the robotic manipulator, taking into account the brush's pressure, orientation, and speed to emulate traditional calligraphy techniques. Experimental results demonstrate the effectiveness of the approach in producing visually authentic Chinese calligraphy with high precision and artistic quality. This work highlights the potential of combining LLM with advanced robotic path planning to bridge the gap between traditional art and robot world.

This paper constructs a simulated CPU assembly line robot system. The system incorporates binocular structured light vision technology for CPU recognition and localization. The reflective surface of the CPU poses a significant challenge for 3D reconstruction, mainly when dealing with tilted angle situations. This inherent characteristic of the CPU adds complexity to the vision system to capture and reconstruct the object's 3D information accurately. This research aims to optimize the vision system's key parameters, balancing cost-effectiveness and the required precision. By achieving the necessary level of accuracy in picking the CPUs to the desired location, our work aims to enhance robotic assembly operations, offering an optimized parameter configuration approach and supporting the needs of modern industrial processes.

Automatic speech recognition (ASR) on low resource languages improves the access of linguistic minorities to technological advantages provided by artificial intelligence (AI). In this paper, we address the problem of data scarcity for the Hong Kong Cantonese language by creating a new Cantonese dataset. Our dataset, Multi-Domain Cantonese Corpus (MDCC), consists of 73.6 hours of clean read speech paired with transcripts, collected from Cantonese audiobooks from Hong Kong. It comprises philosophy, politics, education, culture, lifestyle and family domains, covering a wide range of topics. We also review all existing Cantonese datasets and analyze them according to their speech type, data source, total size and availability. We further conduct experiments with Fairseq S2T Transformer, a state-of-the-art ASR model, on the biggest existing dataset, Common Voice zh-HK, and our proposed MDCC, and the results show the effectiveness of our dataset. In addition, we create a powerful and robust Cantonese ASR model by applying multi-dataset learning on MDCC and Common Voice zh-HK.