Next, we further improve the architecture of [3] by removing IMU inputs and instead feeding a short history of past controls to the controller (blue box in Figure 2), which provides implicit temporal context. Next, the controller training follows a similar imitation learning procedure as in [3]: we first implement a state-based expert that flies through different tracks in simulation; at each timestep, we render the onboard RGB image and record the state-based controller's expert action. The RGB image is passed through the trained U-Net to obtain a binary mask, and we form supervised pairs where the masked image coupled with the past control actions are used to predict the current action to train the controller. Thanks to the Edit API, now we can synthesize essentially arbitrarily many tracks in FalconGym 2.0 to train both perception and controller without additional per-track real-world effort required by [1], [3], [5]. To sample efficiently, our unique design choice is to train on two-gate tracks. Intuitively, the initial state together with two successive gates spans the local geometric variability of longer courses; a controller that performs well on such segments could generalize well to multi-gate tracks by invariance and composition, as is empirically confirmed in Section IV. C. Performance-Guided Refinement Training A straightforward method to collect training data for the visual policy would be to uniformly sample the two-gate track space that is dynamically feasible and observable (as defined at the start of this section). However, uniform sampling can be sample-inefficient in a large high-dimensional workspace. With our Edit API, we can steer training data col- lection toward the visual policy's weak spots and iteratively refine to improve the visual policy.

We propose a new simulator, training approach, and policy architecture, collectively called SOUS VIDE, for end-to-end visual drone navigation. Our trained policies exhibit zero-shot sim-to-real transfer with robust real-world performance using only on-board perception and computation. Our simulator, called FiGS, couples a computationally simple drone dynamics model with a high visual fidelity Gaussian Splatting scene reconstruction. FiGS can quickly simulate drone flights producing photorealistic images at up to 130 fps. We use FiGS to collect 100k-300k observation-action pairs from an expert MPC with privileged state and dynamics information, randomized over dynamics parameters and spatial disturbances. We then distill this expert MPC into an end-to-end visuomotor policy with a lightweight neural architecture, called SV-Net. SV-Net processes color image, optical flow and IMU data streams into low-level body rate and thrust commands at 20Hz onboard a drone. Crucially, SV-Net includes a Rapid Motor Adaptation (RMA) module that adapts at runtime to variations in drone dynamics. In a campaign of 105 hardware experiments, we show SOUS VIDE policies to be robust to 30% mass variations, 40 m/s wind gusts, 60% changes in ambient brightness, shifting or removing objects from the scene, and people moving aggressively through the drone's visual field. Code, data, and experiment videos can be found on our project page: https://stanfordmsl.github.io/SousVide/.

SAFER-Splat (Simultaneous Action Filtering and Environment Reconstruction) is a real-time, scalable, and minimally invasive action filter, based on control barrier functions, for safe robotic navigation in a detailed map constructed at runtime using Gaussian Splatting (GSplat). We propose a novel Control Barrier Function (CBF) that not only induces safety with respect to all Gaussian primitives in the scene, but when synthesized into a controller, is capable of processing hundreds of thousands of Gaussians while maintaining a minimal memory footprint and operating at 15 Hz during online Splat training. Of the total compute time, a small fraction of it consumes GPU resources, enabling uninterrupted training. The safety layer is minimally invasive, correcting robot actions only when they are unsafe. To showcase the safety filter, we also introduce SplatBridge, an open-source software package built with ROS for real-time GSplat mapping for robots. We demonstrate the safety and robustness of our pipeline first in simulation, where our method is 20-50x faster, safer, and less conservative than competing methods based on neural radiance fields. Further, we demonstrate simultaneous GSplat mapping and safety filtering on a drone hardware platform using only on-board perception. We verify that under teleoperation a human pilot cannot invoke a collision. Our videos and codebase can be found at https://chengine.github.io/safer-splat.

Exploring scientific datasets with billions of samples in real-time visualization presents a challenge - balancing high-fidelity rendering with speed. This work introduces a novel renderer - Neural Accelerated Renderer (NAR), that uses the neural deferred rendering framework to visualize large-scale scientific point cloud data. NAR augments a real-time point cloud rendering pipeline with high-quality neural post-processing, making the approach ideal for interactive visualization at scale. Specifically, we train a neural network to learn the point cloud geometry from a high-performance multi-stream rasterizer and capture the desired postprocessing effects from a conventional high-quality renderer. We demonstrate the effectiveness of NAR by visualizing complex multidimensional Lagrangian flow fields and photometric scans of a large terrain and compare the renderings against the state-of-the-art high-quality renderers. Through extensive evaluation, we demonstrate that NAR prioritizes speed and scalability while retaining high visual fidelity. We achieve competitive frame rates of $>$ 126 fps for interactive rendering of $>$ 350M points (i.e., an effective throughput of $>$ 44 billion points per second) using $\sim$12 GB of memory on RTX 2080 Ti GPU. Furthermore, we show that NAR is generalizable across different point clouds with similar visualization needs and the desired post-processing effects could be obtained with substantial high quality even at lower resolutions of the original point cloud, further reducing the memory requirements.

We present Splat-Nav, a real-time navigation pipeline designed to work with environment representations generated by Gaussian Splatting (GSplat), a popular emerging 3D scene representation from computer vision. Splat-Nav consists of two components: 1) Splat-Plan, a safe planning module, and 2) Splat-Loc, a robust pose estimation module. Splat-Plan builds a safe-by-construction polytope corridor through the map based on mathematically rigorous collision constraints and then constructs a B\'ezier curve trajectory through this corridor. Splat-Loc provides a robust state estimation module, leveraging the point-cloud representation inherent in GSplat scenes for global pose initialization, in the absence of prior knowledge, and recursive real-time pose localization, given only RGB images. The most compute-intensive procedures in our navigation pipeline, such as the computation of the B\'ezier trajectories and the pose optimization problem run primarily on the CPU, freeing up GPU resources for GPU-intensive tasks, such as online training of Gaussian Splats. We demonstrate the safety and robustness of our pipeline in both simulation and hardware experiments, where we show online re-planning at 5 Hz and pose estimation at about 25 Hz, an order of magnitude faster than Neural Radiance Field (NeRF)-based navigation methods, thereby enabling real-time navigation.