Contrastive learning is widely used for user modeling in large-scale recommender systems, where standard in-batch negatives implicitly assume universal exposure that any user can be shown any item. On local community platforms such as Karrot, however, exposure is geographically constrained; many user-item pairs are impossible by design yet still treated as negatives during training, diluting the contrastive learning signal. We address this impossible negatives problem and propose Region-Constrained Batch Sampling (RCBS), a simple yet effective batching method that constructs region-homogeneous mini-batches so that users are contrasted primarily against items they could feasibly see. By replacing impossible negatives with feasible ones, RCBS naturally introduces harder and more informative negatives under realistic exposure constraints. With offline evaluations and online A/B tests, we show that RCBS consistently improves user representation quality and consequently enhances home feed ranking, retrieval, and display ads ranking. The resulting user embeddings have been deployed in production across various applications.

This study presents the development of a gait selection strategy for quadrupedal robots capable of responding to external forces. Unlike traditional controllers, our approach directly utilizes information about external forces and introduces a strategy to adapt the robot’s gait patterns accordingly. To simultaneously solve and compare various gait types, we propose a multimodal Model Predictive Control (MPC) framework. This framework dynamically adjusts four distinct gaitstrotting, bounding, pacing, and walking—as well as the contact time with the ground in real-time. The results demonstrate that this approach improves the robot’s ability to withstand disturbances while interacting with external environments, significantly enhancing operational performance and stability.

In this paper, we propose an adaptive safety distance that is adjusted along the uncertain braking duration of the object vehicle resulting in an improvement of driving comfort. In the real world, the object vehicle decelerates for uncertain duration, while the conventional strategies assume that the object vehicle decelerates until full stop. By imposing a constraint on the ego vehicle to stop simultaneously with the object vehicle, the driving comfort is enhanced by activating full braking (FB) only when it is necessary. To accomplish these, two concepts are proposed; effective collision avoidance (ECA) condition and full braking activation parameter (FBAP). ECA refers to a strategy in which the ego vehicle stops simultaneously with the object vehicle to account for its uncertain deceleration duration. FBAP is suggested to determine when to activate FB by adjusting the duration of partial braking (PB). Virtual experiments are conducted strictly with various scenarios to validate the performance of the proposed FBAP-based safety distance. The test results demonstrate that the suggested FBAP-based safety distance is applicable to a wide range of driving speeds, improving driving comfort and performing collision avoidance compared to conventional methods.

As autonomous driving research has actively pro-gressed, software for autonomous vehicles and embedded systems such as Apollo and AutoWare have also been developed, providing a complete set of self-driving modules, including perception, localization and mapping, path planning, prediction, decision making, and control. Most of the researchers currently use these software programs, but many researchers have also studied autonomous driving based on the middleware software termed robot operating system (ROS) before such software was released, especially in academia. Accordingly, we intend to develop ROS-based unmanned RC car equipped with autonomous driving sensors such as LiDAR, radar, VIS/IR cameras, GPS, and IMUs that can provide ROS-based datasets to researchers studying self-driving cars and robots using ROS. In addition, unlike conventional datasets, we acquire dataset not only on road but also pedestrian paths that can be used in both vehicles and robots and provides extreme environmental datasets such as snowfall environments. In this sense, the ROS dataset we created will be helpful to researchers studying autonomous vehicles and robots by using ROS.

This paper presents a compact single-ended inverter-based transceiver with swing improvement for short-reach links. The low output impedance of the transmitter enlarges the output swing and the eye size to overcome large single-ended noise while relaxed impedance matching provides good signal integrity. For good area efficiency, the proposed transmitter utilizes an inverter driver which is much smaller than the conventional source-series termination driver and thus occupies only$42.5 ~\mu \text{m}^{2}$. By taking the advantage of a large signal swing, the receiver consists of only four slicers and latches to minimize area overhead and to simplify the design. The transceiver was fabricated in 28-nm CMOS technology and tested at supply voltage of 1.13 V. The transmitter achieved a large output swing of 850 mV, which is 50.4 % larger than the conventional source-series termination transmitter. At the far-end of a channel consisting of a 1 m SMA cable and a 17 mm printed circuit board trace, the transmitter achieved eye openings of 440 mV and 234 mV at 16 Gb/s (−2.7 dB) and 20 Gb/s (−8 dB), respectively. Even with a large switching noise of 100 mV, thein-situeye at the receiver was measured 114 mV with 7.4 dB loss.

We present the first FFE SST TX layout generator enhanced by various software techniques including a GUI-based template engine. Seven different DRC/LVS-clean TXs were generated in multiple technologies (40nm/65nm/90nm CMOS) for the first time, and achieved adequate maximum data rates: 36Gb/s with 40nm in post-layout simulation; 14Gb/s with 65nm in measurement. Total generation time was less than 5 days, including iterative parameter tuning by a human designer and computation (30 minutes for TX core, 8 hours for power network). Fast post-layout analysis of TX’s performance-power trade-off was enabled by the presented generator for the first time.

This paper investigates the channel estimation schemes for tracking rapid time variant channels in IEEE 802. 11p systems. To overcome the problems of the existing preamble based channel estimation, various data-pilot aided (DPA) algorithms have been developed. However, their performance is not sufficient to meet the advanced V2X use cases. In this paper, we propose a novel two step channel estimation scheme which outperforms the conventional DPA designs. For the first step, we develop an enhanced time-domain reliability test and frequency domain interpolation scheme by exploiting the Euclidean distance between the received signals and constellation points, and the channel information in the virtual subcarriers to improve the prediction accuracy at high signal-to-noise ratio (SNR). In the second step, we attenuate the noise components from the estimated channel frequency responses in the previous step to address the low SNR performance gain. To this end, we adopt the time domain least square estimation strategy. The proposed scheme exhibits dramatic performance gain over the SNR with marginal complexity increase compared to the conventional DPA algorithms. Finally, simulation results verify the efficiency of the proposed scheme.

In this paper, we propose a novel deep learning based channel estimation scheme for IEEE 802.11p vehicle-to-everything (V2X) communication systems. A major challenge in the V2X system is to grasp complicated variations and distortion of the channels due to high mobility. To address the issue, the data-pilot aided (DPA) channel estimation schemes have been investigated, but the performance is still unsatisfactory due to the error propagation issue. To tackle the problem, in this paper, we introduce a machine learning technique based on an artificial neural network so called autoencoder (AE) to the conventional DPA process. To reduce the size of the neural network, thereby minimizing the receiver complexity, we design the AE such that it learns the channel frequency characteristics only. Then, we use the trained AE for updating the channel estimates obtained from the DPA process. The trained AE is capable of recovering estimation errors based on the channel frequency correlation, and thus help us attenuate the error propagation issue of the DPA process. The proposed scheme is scalable from the conventional systems, because we can simply put or remove the AE in the middle of the DPA process. In addition, it is verified from simulation results that the proposed scheme exhibits a dramatic performance gain over the conventional V2X channel estimation schemes.

A modeling support system that provides an easy and fast FE-modeling for the static and durability analysis of the lower arm in an automobile suspension module is described. The system can exclude human interactions such as meshing using pre-defined shell elements and can impose complicated boundary and loading conditions via a multi-point constraints technique. The platform of this system is implemented based on MSC.PATRAN, and MSC.NASTRAN and MSC.FATIGUE are utilized as the solver. The parametric geometry modeling tool utilizing CATIA V5 is linked with the modeling support system, which enables changes in 3D models, that occur frequently in an early stage of the design process, to be taken into account. The integration techniques using XML-based wrapper enable to integrate the overall process. This system was applied to an actual work process to calculate the fatigue durability of the lower arm in an automobile suspension module, and time and cost reduction for this analysis were validated.