Egocentric human motion generation and forecasting with scene-context is crucial for enhancing AR/VR experiences, improving human-robot interaction, advancing assistive technologies, and enabling adaptive healthcare solutions by accurately predicting and simulating movement from a first-person perspective. However, existing methods primarily focus on third-person motion synthesis with structured 3D scene contexts, limiting their effectiveness in real-world egocentric settings where limited field of view, frequent occlusions, and dynamic cameras hinder scene perception. To bridge this gap, we introduce Egocentric Motion Generation and Egocentric Motion Forecasting, two novel tasks that utilize first-person images for scene-aware motion synthesis without relying on explicit 3D scene. We propose UniEgoMotion, a unified conditional motion diffusion model with a novel head-centric motion representation tailored for egocentric devices. UniEgoMotion's simple yet effective design supports egocentric motion reconstruction, forecasting, and generation from first-person visual inputs in a unified framework. Unlike previous works that overlook scene semantics, our model effectively extracts image-based scene context to infer plausible 3D motion. To facilitate training, we introduce EE4D-Motion, a large-scale dataset derived from EgoExo4D, augmented with pseudo-ground-truth 3D motion annotations. UniEgoMotion achieves state-of-the-art performance in egocentric motion reconstruction and is the first to generate motion from a single egocentric image. Extensive evaluations demonstrate the effectiveness of our unified framework, setting a new benchmark for egocentric motion modeling and unlocking new possibilities for egocentric applications.

With the focus on data-driven scenario-based methods for the safety assessment of autonomous driving systems, there is a need to generate scenario databases from naturalistic driving data. In this study, we look at the lane wandering and the cut-out scenario, two scenarios that have received little attention to date. The paper is structured as follows: first of all, we model the two scenarios and define parameters necessary to accurately describe them. After that we show how algorithms can be used to detect the scenarios automatically in a large naturalistic driving database recorded on German highways using vehicles equipped with pre-series sensors. Following that, we analyze selected scenario parameters in detail and discuss the findings of the scenario data analysis to derive recommendations for the safety assessment of autonomous driving systems. We were able to show that lane wandering scenarios may in many cases lead to safety critical situations due to the significant lateral velocities and that cut-out scenarios are especially critical if they involve a lane change to the left lane.

In this study, a novel self-supervised earning (SSL) method is proposed, which considers SSL in terms of variational inference to learn not only representation but also representation uncertainties. SSL is a method of learning representations without labels by maximizing the similarity between image representations of different augmented views of an image. Meanwhile, variational autoencoder (VAE) is an unsupervised representation learning method that trains a probabilistic generative model with variational inference. Both VAE and SSL can learn representations without labels, but their relationship has not been investigated in the past. Herein, the theoretical relationship between SSL and variational inference has been clarified. Furthermore, a novel method, namely variational inference SimSiam (VI-SimSiam), has been proposed. VI-SimSiam can predict the representation uncertainty by interpreting SimSiam with variational inference and defining the latent space distribution. The present experiments qualitatively show that VI-SimSiam could learn uncertainty by comparing input images and predicted uncertainties. Additionally, we described a relationship between estimated uncertainty and classification accuracy.

The generation of parametrized test scenarios that prove the safety of automated driving system is still unresolved. The state of the art in data-driven test case generation presents more and more complex approaches, neglecting the goals of comprehensibility and practicality and hardly consider the requirement of realistic test case design. In this paper, we further develop our search-based test case generation methodology [1]. Among others, we introduce the novel approach of boundary functions where dependencies in the edge areas of a 2-dimensional parameter space are automatically detected and transformed into sampling restrictions for realistic test case design. Further, we apply the methodology on the unprotected left turn scenario based on an urban naturalistic driving dataset recorded in Germany [2]. Here, we present an advanced modeling approach and criticality metric that is suitable to generate test cases that evaluate the Vehicle under Test’s capability to flexibly re-plan its driving trajectory during approaching. The generated test cases outperform a common sampling approach in terms of criticality and coverage and are applicable to comparable complex urban scenarios.

This study enhances automated driving scenario-based safety assessment methods previously developed for highways, and enables their application to urban areas. First, we propose a methodology for matching open source map data with naturalistic driving data recorded with test vehicles. The methodology proposed proved feasible detecting various geometry-related scenarios and can contribute to overcome the difficulties to create representative real driving urban scenario databases that cover such geometries. Second, a search-based test case generation methodology previously developed to fulfill requirements of severity, exposure and realism with a focus on highways, is further developed and adapted to active urban scenarios. Active scenarios require an active maneuver decision of the Vehicle under Test and have not been considered in related work so far. To show the feasibility of the methodologies proposed, we apply them to a set of Left Turn Across Path / Opposite Direction scenarios, extracted from an existing urban driving database. The map matching and the search-based test case generation methodology succeeded in deriving test cases, which equally account for exposure and coverage criteria for normal driving situations in urban settings.

In developing automatic platooning of trucks as an energy-saving technology, the reliable driving of the platooned trucks is a primary objective for public implementation and future applications. At the same time, there is also an emergency requirement to ensure the safety of the driving experiment in the automatic platooning of trucks, including the conditions of a system failure. This paper presents a detailed experimental study on emergency avoidance braking for the automatic platooning of trucks using a driving simulator (DS) and an actual-vehicle experiment. In addition, a modification on the braking capability of the trucks of a platoon was applied for safety control. Therefore, human drivers can brake without risking a rear-end collision, in the case of an emergency for a failure in automatic platooning. Initially, an experimental platform was built to reproduce the automatic platooning of trucks in an advanced DS system. Assuming system failure and the emergency deceleration of the preceding truck without warning, the behavior of the driver in the following truck was studied in terms of emergency avoidance of a collision. In particular, with different settings for the mean maximum decelerations of the brake system of the following truck, the stopping gap distances and driver reaction times were analyzed in the driving experiment using the advanced DS and an actual vehicle. The experimental results indicated that emergency braking is an effective method for avoiding a rear-end collision when there is a system failure in the automatic platooning, resulting in the mean maximum deceleration for the following truck being higher than that for the preceding truck.

In this paper, we propose a novel method to detect music genre borders for the music genre classification. The music genre classification is getting more important because music is influenced by an increasing amount of different musical styles. A general approach to classify music genres is a single genre labeling that usually gives the meaning of inherent stylistic elements to a musical piece. However this gives ambiguity in case of a music piece having multiple genres. To solve the problem, we consider separating the multi-label classification task into the single-label genre classification task. We propose a novel method to detect music genre borders for multi-label genre classification. The proposed method can find borderlines of different genres in music. Moreover, it is strongly expected to realize the multi-label genre classification to apply the single-label genre classification to each detected music segment.

The Mining Software Repositories (MSR) field integrates and analyzes data stored in repositories such as source control and bug repositories to support practitioners. Given the abundance of repository data, scaling up MSR analyses has become a major challenge. Recently, researchers have experimented with conventional techniques like a supercomputer or cloud computing, but these are either too expensive or too hard to configure. This paper proposes to scale up MSR analysis using “general-purpose computing on graphics processing units” (GPGPU) on off-the-shelf video cards. In a representative MSR case study to measure co-change on version history of the Eclipse project, we find that the GPU approach is up to a factor of 43.9 faster than a CPU-only approach.

Continuous haptic feedback can improve manual control task performance and application methods on steering wheel (haptic steering guidance) have been studied. However, the current haptic steering guidance systems assume there is an average, constant driver's response to force (which can be quantified as the admittance). To improve the performance of haptic steering guidance, the guidance system should be adaptive to the inter and intra-driver variability in admittance. To achieve this we need to be able to get accurate, non-evasive estimates of driver neuromuscular admittance. We believe the gripping force with which drivers control the steering wheel might be a good parameter to estimate admittance. The goal of this paper is to investigate the correlation between grip strength and human admittance of a driver holding the steering wheel. A relax task and a position task with two different grip conditions, loose and tight, are performed. The results of the experiment show that there should be an inverse relationship between grip strength and admittance. Whether it is possible to differentiate admittance between tasks through grip strength alone remains to be seen as we could not measure grip strength directly. Future experiments with grip pressure sensors will be carried out to establish a quantitative correlation between grip strength and neuromuscular admittance.

A flexible symbol-timing synchronization method is a one that uses a common sampling clock to find synchronization points for radio communication systems that have different symbol rates. This method estimates synchronization points from state patterns calculated using the symbol rate, sampling clock, and number of observed symbols. Decreasing the number of state pattern is one of best ways to reduce the amount of device resources needed to store the patterns. In this paper, we propose a new pattern generation method in which the number of generated patterns does not increase when the sampling clocks of the communications systems are different. To show the feasibility of this method for symbol-timing synchronization, we analyzed a relationship between the number of samples and the number of state patterns and calculated the BER (bit error rate) in AWGN (additive white Gaussian noise) and one-path flat Rayleigh fading environments by computer simulation.

A scalable MPEG-4 video codec architecture is proposed to achieve low power consumption and high cost-effectiveness for IMT-2000 multimedia applications. The MPEG-4 video codec consists of a 16-bit multimedia-extended RISC processor and dedicated hardware accelerators, which bring about both low power consumption and programmability. The proposed architecture is extended and applied for the development of two MPEG-4 LSIs. One is an MPEG-4 video codec LSI, which performs an MPEG-4 video encoding and decoding at 15 frames per second with quarter common intermediate format. The other is an MPEG-4 audiovisual LSI, containing three 16-bit RISC processors and a 16-Mbit embedded DRAM, executes the major functions of 3GPP 3G-324M video telephony for IMT-2000 applications. By introducing the optimization of the embedded DRAM configuration, clock gating technique, and low power motion estimation, the MPEG-4 audiovisual LSI consumes only 240 mW when it activates MPEG-4 video SP@L1 codec, the AMR speech codec, and the H.223 annex B multiplex at 60 MHz clock rate.

We propose a coordinate-by-coordinate interleaved trellis coded QPSK with the T-algorithm. A rate 1/2 convolutional code with constraint lengths of 7 and 15 are evaluated on Rayleigh fading channels in terms of the bit error rate (BER) by an analysis and a computer simulation. As the effective code length (ECL) is equal to the code constraint length for the case of a QPSK system, the proposed system achieves a satisfactory BER performance even in the situation where no channel state information (CSI) is available at the decoder. Further, in order to reduce the decoding complexity, we employ the T-algorithm. It is shown that as the T-algorithm can track the fluctuating gains introduced by the fading channel, we can achieve a satisfactory BER performance with 0.01% of the decoding complexity of the Viterbi algorithm.