Non-rigid registration is essential for augmented reality-guided laparoscopic liver surgery, as it enables the fusion of preoperative information such as tumor location and vascular structures into the limited intraoperative view, thereby enhancing surgical navigation. A prerequisite is the accurate prediction of intraoperative liver deformation, which remains highly challenging due to factors such as large deformation caused by pneumoperitoneum, respiration and tool interaction as well as noisy intraoperative data, and limited field of view due to occlusion and constrained camera movement. To address these challenges, we introduce PIVOTS, a Preoperative to Intraoperative VOlume-To-Surface registration neural network that directly takes point clouds as input for deformation prediction. The geometric feature extraction encoder allows multi-resolution feature extraction, and the decoder, comprising inter-modality cross attention modules, enables information exchange between pre- and intraoperative features and accurate multi-level displacement prediction. We train the neural network on a large synthetic dataset created using a biomechanical simulation pipeline that explicitly targets the mentioned intraoperative challenges and validate its performance on both synthetic and real datasets. Results demonstrate superior registration performance of our method compared to baseline methods, exhibiting strong robustness against high amounts of noise, large deformation, and various levels of intraoperative visibility. The network is fast enough to run multiple times per second and directly generalizes to new patients without retraining. We publish training and test sets as evaluation benchmarks in an effort to contribute to the development of more robust liver registration methods based on volume-to-surface data. Code, docker container and datasets are available athttps://github.com/pengliu-nct/PIVOTS.

For semiconductor manufacturing factories, the creation of a master schedule spanning several weeks is crucial for outlining the production timeline, including processing schedules and lot locations. However, the semiconductor assembly line operates within a dynamic environment that is subject to random disruptions, such as machine failures. These disruptions can lead to delays and time window violation, thereby rendering the master schedule suboptimal or even infeasible. This paper specifically addresses the impact of long machine failures, defined as those exceeding an hour, which significantly disrupt the assembly line’s operations. To confront this challenge, we propose a decentralized genetic algorithm tailored to adjust a short-term master schedule while accommodating re-entrant operations and adhering to time window constraints. Our experiments are conducted using real-world datasets, and the results illustrate that the proposed method effectively reduces delays and prevents time window violations within limited computational time.

With the growing adoption of light detection and ranging (LiDAR) technology and the increasing resolution of captured data, efficient point cloud compression (PCC) has become a critical challenge. While PCC is essential for reducing bandwidth and storage demands, existing octree-based learned PCC methods face two fundamental bottlenecks: 1) octree construction and serialization that involve irregular, pointwise memory accesses that are difficult to parallelize and 2) autoregressive entropy model inference that requires heavy computation. These issues lead to high latency and energy consumption, making real-time deployment on edge devices impractical. This article introduces COPIC, a hardware accelerator designed for real-time PCC on edge devices. COPIC integrates two key components. The first is OctCAM, a content-addressable-memory (CAM)-based module for rapid octree construction and serialization. By enabling hardware-level parallel search, OctCAM significantly reduces the latency and energy consumption caused by irregular memory access patterns in octree processing. The second is PCC-Engine, a dedicated neural network inference module. Combined with a lightweight PCC-TinyAttention network and a window-based key-value caching approach, it further minimizes execution latency and power usage. Experimental results show that COPIC achieves a$25.9\times $speedup compared to GPU implementations, with a total processing latency of 40.1 ms and an average energy consumption of 0.23 J per frame, while delivering a compression rate 12.4% higher than standard proposals.

In semiconductor packaging line, a master schedule is normally created every shift to optimize production for a three-week horizon. However, semiconductor packaging lines are susceptible to machine failures, causing the master schedule to be sub-optimal or even infeasible. Specifically, machine failures can result in due dates not to be met and time window constraints to be violated. In this study, we classify machine failures in semiconductor packaging lines into two categories: short and long machine failures, which can be identified when the failure happens. To handle short machine failures, extra time is added into the processing time of each lot to make the master schedule robust. When a long machine failure occurs, a mixed integer programming model is formulated to adjust the master schedule. The master schedule is taken as a warm start, and a short period schedule is obtained using CPLEX for the semiconductor packaging line to follow immediately. In this way, the semiconductor packaging line can quickly respond to long machine failure without replacing the whole master schedule or giving the master scheduler enough time to remake a new master schedule. Thus, the negative impact of machine failure is mitigated. Using the data from shop floor, a simulation model is developed with SimPy to simulate a real-world semiconductor packaging line and evaluate the proposed method. The experiment results show that the proposed method can achieve fast response to machine failures in semiconductor packaging lines.Note to Practitioners—The semiconductor packaging line operates as a highly intricate production system. Its inherent flexibility allows for the simultaneous processing of diverse products from various orders. However, this flexibility necessitates adherence to a master schedule, often created without accounting for potential disruptions, such as machine failures. When not promptly addressed with efficient production control measures, machine failures can lead to production losses and product quality concerns. Moisture absorption and die surface oxidation are common quality issues that arise in the semiconductor packaging line, primarily caused by extended wait times in buffers. To equip production engineers with an effective solution for real production settings, this study introduces a practical tool to swiftly respond to machine failures. By implementing this tool, production teams can mitigate the impact of disruptions and ensure smoother operations in the semiconductor packaging process.

The use of Light Detection and Ranging (LiDAR) for sensing has continuously improved the precision and performance of autonomous driving. At the same time, the large number of high-precision point clouds generated by LiDAR require real-time processing, and the range search is the key part of the processing pipeline. Content-Addressable Memory (CAM) has proven its efficiency for search tasks on switches and routers, but so far, there is still a lack of exploration on its application in point cloud range search. In this work, we propose CAMPER, a CAM-centered accelerator, aiming to explore the potential of CAM for point cloud range search. We developed a ripple comparison 13T (RC-13T) CAM cell for distance comparison, designed a spatial approximation search algorithm based on Chebyshev distance, and discussed the flexibility and scalability of the architecture. The results show that in the range search task of 64k@64k points, CAMPER achieves a latency of 0.83ms and a power consumption of 114.6mW. Compared with GPU, the throughput is increased by 10.4×; compared with SOTA accelerator, the energy efficiency is increased by about 228×.

Multiple‐input‐multiple‐output (MIMO) radar is attractive in moving targets imaging, which is able to solve the difficulty of complex motion compensation. In this article, a three‐dimensional imaging method using bistatic MIMO radar is proposed. Compared with monostatic MIMO radar, the bistatic system can provide the complementary information, and the imaging process is not the same as the monostatic case. Furthermore, considering the image sparsity and the spatial limitation of radar targets, a fast smoothed L0 norm algorithm is proposed to achieve the high resolution in cross‐range directions with limited antennas. The experimental results demonstrate the validity and efficiency of the proposed method.