The rapid advancements in autonomous driving have introduced increasingly complex, real-time GPU-bound tasks critical for reliable vehicle operation. However, the proprietary nature of these autonomous systems and closed-source GPU drivers hinder fine-grained control over GPU executions, often resulting in missed deadlines that compromise vehicle performance. To address this, we present UrgenGo, a non-intrusive, urgency-aware GPU scheduling system that operates without access to application source code. UrgenGo implicitly prioritizes GPU executions through transparent kernel launch manipulation, employing task-level stream binding, delayed kernel launching, and batched kernel launch synchronization. We conducted extensive real-world evaluations in collaboration with a self-driving startup, developing 11 GPU-bound task chains for a realistic autonomous navigation application and implementing our system on a self-driving bus. Our results show a significant 61% reduction in the overall deadline miss ratio, compared to the state-of-the-art GPU scheduler that requires source code modifications.

Abstract Constructing and sharing 3D maps is essential for many applications, including autonomous driving and augmented reality. Recently, 3D Gaussian splatting has emerged as a promising approach for accurate 3D reconstruction. However, a practical map‐sharing system that features high‐fidelity, continuous updates, and network efficiency remains elusive. To address these challenges, we introduce GS‐Share, a photorealistic map‐sharing system with a compact representation. The core of GS‐Share includes anchor‐based global map construction, virtual‐image‐based map enhancement, and incremental map update. We evaluate GS‐Share against state‐of‐the‐art methods, demonstrating that our system achieves higher fidelity, particularly for extrapolated views, with improvements of 11%, 22%, and 74% in PSNR, LPIPS, and Depth L1, respectively. Furthermore, GS‐Share is significantly more compact, reducing map transmission overhead by 36%.

Constructing precise 3D maps is crucial for the development of future map-based systems such as self-driving and navigation. However, generating these maps in complex environments, such as multi-level parking garages or shopping malls, remains a formidable challenge. In this paper, we introduce a participatory sensing approach that delegates map-building tasks to map users, thereby enabling cost-effective and continuous data collection. The proposed method harnesses the collective efforts of users, facilitating the expansion and ongoing update of the maps as the environment evolves.

It has been well recognized that fusing the complementary information from depth-aware LiDAR point clouds and semantic-rich stereo images would benefit 3D object detection. Nevertheless, it is non-trivial to explore the inherently unnatural interaction between sparse 3D points and dense 2D pixels. To ease this difficulty, the recent approaches generally project the 3D points onto the 2D image plane to sample the image data and then aggregate the data at the points. However, these approaches often suffer from the mismatch between the resolution of point clouds and RGB images, leading to sub-optimal performance. Specifically, taking the sparse points as the multi-modal data aggregation locations causes severe information loss for high-resolution images, which in turn undermines the effectiveness of multi-sensor fusion. In this paper, we presentVPFNet—a new architecture that cleverly aligns and aggregates the point cloud and image data at the “virtual” points. Particularly, with their density lying between that of the 3D points and 2D pixels, the virtual points can nicely bridge the resolution gap between the two sensors, and thus preserve more information for processing. Moreover, we also investigate the data augmentation techniques that can be applied to both point clouds and RGB images, as the data augmentation has made non-negligible contribution towards 3D object detectors to date. We have conducted extensive experiments on KITTI dataset, and have observed good performance compared to the state-of-the-art methods. Remarkably, ourVPFNetachieves 83.21% moderate$AP_{3D}$and 91.86% moderate$AP_{BEV}$on the KITTI test set. The network design also takes computation efficiency into consideration – we can achieve a FPS of 15 on a single NVIDIA RTX 2080Ti GPU.

This paper describes the design of a powered knee- and-ankle transfemoral prosthetic leg, which implements high torque density actuators with low-reduction transmissions. The low reduction of the transmission coupled with a high-torque and low-speed motor creates an actuator with low mechanical impedance and high backdrivability. This style of actuation presents several possible benefits over modern actuation styles implemented in emerging robotic prosthetic legs. Such benefits include free-swinging knee motion, compliance with the ground, negligible unmodeled actuator dynamics, and greater potential for power regeneration. Benchtop validation experiments were conducted to verify some of these benefits. Backdrive and free-swinging knee tests confirm that both joints can be backdriven by small torques (~3 Nm). Bandwidth tests reveal that the actuator is capable of achieving frequencies required for walking and running. Lastly, open-loop impedance control tests prove that the intrinsic impedance and unmodeled dynamics of the actuator are sufficiently small to control joint impedance without torque feedback.

This paper presents the mechatronic design and experimental validation of a novel powered knee-ankle orthosis for testing torque-driven rehabilitation control strategies. The modular actuator of the orthosis is designed with a torque dense motor and a custom low-ratio transmission (24:1) to provide mechanical transparency to the user, allowing them to actively contribute to their joint kinematics during gait training. The 4.88 kg orthosis utilizes frameless components and light materials, such as aluminum alloy and carbon fiber, to reduce its mass. A human subject experiment demonstrates accurate torque control with high output torque during stance and low backdrive torque during swing at fast walking speeds. This work shows that backdrivability, precise torque control, high torque output, and light weight can be achieved in a powered orthosis without the high cost and complexity of variable transmissions, clutches, and/or series elastic components.

Traditional control methodologies of rehabilitation orthoses/exoskeletons aim at replicating normal kinematics and thus fall into the category of kinematic control. This control paradigm depends on pre-defined reference trajectories, which can be difficult to adjust between different locomotor tasks and human subjects. An alternative control category, kinetic control, enforces kinetic goals (e.g., torques or energy) instead of kinematic trajectories, which could provide a flexible learning environment for the user while freeing up therapists to make corrections. We propose that the theory of underactuated potential energy shaping, which falls into the category of kinetic control, could be used to generate virtual body-weight support for stroke gait rehabilitation. After deriving the nonlinear control law and simulating it on a human-like biped model, we implemented this controller on a powered ankle-foot orthosis that was designed specifically for testing torque control strategies. Experimental results with an able-bodied human subject demonstrate the feasibility of the control approach for both positive and negative virtual body-weight augmentation.