Unpredictable and complex aerodynamic effects pose significant challenges to achieving precise flight control, emphasizing the necessity of adaptive control via data- driven models. Moreover, real hardware usually requires high-frequency and has limited on-chip computation, making it challenging to balance the model complexity and computational cost. To address these challenges, we incorporate a linearized Gaussian process (GP) to model the external aerodynamics and combine it with linear model predictive control, enabling real-time computability. More importantly, to compensate for the control performance sacrificed by GP linearization and reduce on-chip GP computations, we design active data collection strategies using Bayesian optimization with additive GP, reducing the performance sacrifice as much as possible. Specifically, we decompose the performance into force and trajectory partitions, where the force model is for the downstream controller, and the trajectory model is used to guide collection. Experimental results show that we can achieve comparable tracking errors with full GP (not real-time computable) while maintaining real-time computable on the real Crazyflies.

Small object detection has been a challenging problem in the field of object detection. There has been some works that proposes improvements for this task, such as adding several attention blocks or changing the whole structure of feature fusion networks. However, the computation cost of these models is large, which makes deploying a real-time object detection system unfeasible, while leaving room for improvement. To this end, an improved YOLOv5 model: HIC-YOLOv5 is proposed to address the aforementioned problems. Firstly, an additional prediction head specific to small objects is added to provide a higher-resolution feature map for better prediction. Secondly, an involution block is adopted between the backbone and neck to increase channel information of the feature map. Moreover, an attention mechanism named CBAM is applied at the end of the backbone, thus not only decreasing the computation cost compared with previous works but also emphasizing the important information in both channel and spatial domain. Our result shows that HIC-YOLOv5 has improved mAP@[.5:.95] by 6.42% and [email protected] by 9.38% on VisDrone-2019-DET dataset.

Humanoid robots are promising approach to automating patient interviews routinely conducted by medical staff. Their human-like appearance enables them to use the full gamut of verbal and behavioral cues that are critical to a successful interview. On the other hand, anthropomorphism can induce expectations of human-level performance by the robot. Not meeting such expectations degrades the quality of interaction. Specifically, humans expect rich real-time interactions during speech exchange, such as backchanneling and barge-ins. The nature of the patient interview task differs from most other scenarios where task oriented dialogue systems have been used, as there is increased potential of engagement breakdown during interaction. We describe a dialogue system architecture that improves the performance of humanoid robots on the patient interview task. Our architecture adds a nested inner real-time control loop to improve the timeliness of the robot’s responses based on the notion of "stance", an elaboration of the concept of a "turn", common in most existing dialogue systems. It also expands the dialogue state to monitor not only task progress, but also human engagement. Experiments using a humanoid robot running our proposed architecture reveal improved performance on interview tasks in terms of the perceived timeliness of responses and users’ impressions of the system.

Micro-expressions (MEs) are involuntary and subtle facial expressions that are thought to reveal feelings people are trying to hide. ME spotting detects the temporal intervals containing MEs in videos. Detecting such quick and subtle motions from long videos is difficult. Recent works leverage detailed facial motion representations, such as the optical flow, and deep learning models, leading to high computational complexity. To reduce computational complexity and achieve real-time operation, we propose RMES, a real-time ME spotting framework. We represent motion using phase computed by Riesz Pyramid, and feed this motion representation into a three-stream shallow CNN, which predicts the likelihood of each frame belonging to an ME. In comparison to optical flow, phase provides more localized motion estimates, which are essential for ME spotting, resulting in higher performance. Using phase also reduces the required computation of the ME spotting pipeline by 77.8%. Despite its relative simplicity and low computational complexity, our framework achieves state-of-the-art performance on two public datasets: CAS(ME)2and SAMM Long Videos.

Data-driven mobile network management hinges on accurate traffic measurements, which routinely require expensive specialized equipment and substantial local storage capabilities, and bear high data transfer overheads. To overcome these challenges, in this paper we propose Spider, a deep-learning-driven mobile traffic measurement collection and reconstruction framework, which reduces the cost of data collection while retaining state-of-the-art accuracy in inferring mobile traffic consumption with fine geographic granularity. Spider harnesses Reinforcement Learning and tackles large action spaces to train a policy network that selectively samples a minimal number of cells where data should be collected. We further introduce a fast and accurate neural model that extracts spatiotemporal correlations from historical data to reconstruct network-wide traffic consumption based on sparse measurements. Experiments we conduct with a real-world mobile traffic dataset demonstrate that Spider samples 48% fewer cells as compared to several benchmarks considered, and yields up to 67% lower reconstruction errors than state-of-the-art interpolation methods. Moreover, our framework can adapt to previously unseen traffic patterns.