Sebastian Scherer
YOU?
Author Swipe
View article: RAVEN: Resilient Aerial Navigation via Open-Set Semantic Memory and Behavior Adaptation
RAVEN: Resilient Aerial Navigation via Open-Set Semantic Memory and Behavior Adaptation Open
Aerial outdoor semantic navigation requires robots to explore large, unstructured environments to locate target objects. Recent advances in semantic navigation have demonstrated open-set object-goal navigation in indoor settings, but these…
View article: The Case for Negative Data: From Crash Reports to Counterfactuals for Reasonable Driving
The Case for Negative Data: From Crash Reports to Counterfactuals for Reasonable Driving Open
Learning-based autonomous driving systems are trained mostly on incident-free data, offering little guidance near safety-performance boundaries. Real crash reports contain precisely the contrastive evidence needed, but they are hard to use…
View article: SmokeSeer: 3D Gaussian Splatting for Smoke Removal and Scene Reconstruction
SmokeSeer: 3D Gaussian Splatting for Smoke Removal and Scene Reconstruction Open
Smoke in real-world scenes can severely degrade image quality and hamper visibility. Recent image restoration methods either rely on data-driven priors that are susceptible to hallucinations, or are limited to static low-density smoke. We …
View article: AutoODD: Agentic Audits via Bayesian Red Teaming in Black-Box Models
AutoODD: Agentic Audits via Bayesian Red Teaming in Black-Box Models Open
Specialized machine learning models, regardless of architecture and training, are susceptible to failures in deployment. With their increasing use in high risk situations, the ability to audit these models by determining their operational …
View article: UFM: A Simple Path towards Unified Dense Correspondence with Flow
UFM: A Simple Path towards Unified Dense Correspondence with Flow Open
Dense image correspondence is central to many applications, such as visual odometry, 3D reconstruction, object association, and re-identification. Historically, dense correspondence has been tackled separately for wide-baseline scenarios a…
View article: TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigation
TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigation Open
We present TartanGround, a large-scale, multi-modal dataset to advance the perception and autonomy of ground robots operating in diverse environments. This dataset, collected in various photorealistic simulation environments includes multi…
View article: BETTY Dataset: A Multi-modal Dataset for Full-Stack Autonomy
BETTY Dataset: A Multi-modal Dataset for Full-Stack Autonomy Open
We present the BETTY dataset, a large-scale, multi-modal dataset collected on several autonomous racing vehicles, targeting supervised and self-supervised state estimation, dynamics modeling, motion forecasting, perception, and more. Exist…
View article: Demonstrating ViSafe: Vision-enabled Safety for High-speed Detect and Avoid
Demonstrating ViSafe: Vision-enabled Safety for High-speed Detect and Avoid Open
Assured safe-separation is essential for achieving seamless high-density operation of airborne vehicles in a shared airspace. To equip resource-constrained aerial systems with this safety-critical capability, we present ViSafe, a high-spee…
View article: Flying Hand: End-Effector-Centric Framework for Versatile Aerial Manipulation Teleoperation and Policy Learning
Flying Hand: End-Effector-Centric Framework for Versatile Aerial Manipulation Teleoperation and Policy Learning Open
Aerial manipulation has recently attracted increasing interest from both industry and academia. Previous approaches have demonstrated success in various specific tasks. However, their hardware design and control frameworks are often tightl…
View article: IA-TIGRIS: An Incremental and Adaptive Sampling-Based Planner for Online Informative Path Planning
IA-TIGRIS: An Incremental and Adaptive Sampling-Based Planner for Online Informative Path Planning Open
Planning paths that maximize information gain for robotic platforms has wide-ranging applications and significant potential impact. To effectively adapt to real-time data collection, informative path planning must be computed online and be…
View article: [Withdrawn] AirIO: Learning Inertial Odometry with Enhanced IMU Feature Observability — air-io.github.io
[Withdrawn] AirIO: Learning Inertial Odometry with Enhanced IMU Feature Observability — air-io.github.io Open
This manuscript has been withdrawn.
View article: AirIO: Learning Inertial Odometry with Enhanced IMU Feature Observability
AirIO: Learning Inertial Odometry with Enhanced IMU Feature Observability Open
Inertial odometry (IO) using only Inertial Measurement Units (IMUs) offers a lightweight and cost-effective solution for Unmanned Aerial Vehicle (UAV) applications, yet existing learning-based IO models often fail to generalize to UAVs due…
View article: Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video
Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video Open
We aim to redefine robust ego-motion estimation and photorealistic 3D reconstruction by addressing a critical limitation: the reliance on noise-free data in existing models. While such sanitized conditions simplify evaluation, they fail to…
View article: CoCap: Coordinated motion Capture for multi-actor scenes in outdoor environments
CoCap: Coordinated motion Capture for multi-actor scenes in outdoor environments Open
Motion capture has become increasingly important, not only in computer animation but also in emerging fields like the virtual reality, bioinformatics, and humanoid training. Capturing outdoor environments offers extended horizon scenes but…
View article: SALON: Self-supervised Adaptive Learning for Off-road Navigation
SALON: Self-supervised Adaptive Learning for Off-road Navigation Open
Autonomous robot navigation in off-road environments presents a number of challenges due to its lack of structure, making it difficult to handcraft robust heuristics for diverse scenarios. While learned methods using hand labels or self-su…
View article: SuperLoc: The Key to Robust LiDAR-Inertial Localization Lies in Predicting Alignment Risks
SuperLoc: The Key to Robust LiDAR-Inertial Localization Lies in Predicting Alignment Risks Open
Map-based LiDAR localization, while widely used in autonomous systems, faces significant challenges in degraded environments due to lacking distinct geometric features. This paper introduces SuperLoc, a robust LiDAR localization package th…
View article: MapEx: Indoor Structure Exploration with Probabilistic Information Gain from Global Map Predictions
MapEx: Indoor Structure Exploration with Probabilistic Information Gain from Global Map Predictions Open
Exploration is a critical challenge in robotics, centered on understanding unknown environments. In this work, we focus on robots exploring structured indoor environments which are often predictable and composed of repeating patterns. Most…
View article: MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry
MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry Open
We propose the MAC-VO, a novel learning-based stereo VO that leverages the learned metrics-aware matching uncertainty for dual purposes: selecting keypoint and weighing the residual in pose graph optimization. Compared to traditional geome…
View article: FIReStereo: Forest InfraRed Stereo Dataset for UAS Depth Perception in Visually Degraded Environments
FIReStereo: Forest InfraRed Stereo Dataset for UAS Depth Perception in Visually Degraded Environments Open
Robust depth perception in visually-degraded environments is crucial for autonomous aerial systems. Thermal imaging cameras, which capture infrared radiation, are robust to visual degradation. However, due to lack of a large-scale dataset,…
View article: AmeliaTF: A Large Model and Dataset for Airport Surface Movement Forecasting
AmeliaTF: A Large Model and Dataset for Airport Surface Movement Forecasting Open
Demand for air travel is rising, straining existing aviation infrastructure. In the US, more than 90% of airport control towers are understaffed, falling short of FAA and union standards. This, in part, has contributed to an uptick in near…
View article: UNRealNet: Learning Uncertainty-Aware Navigation Features from High-Fidelity Scans of Real Environments
UNRealNet: Learning Uncertainty-Aware Navigation Features from High-Fidelity Scans of Real Environments Open
Traversability estimation in rugged, unstructured environments remains a challenging problem in field robotics. Often, the need for precise, accurate traversability estimation is in direct opposition to the limited sensing and compute capa…
View article: Map It Anywhere (MIA): Empowering Bird's Eye View Mapping using Large-scale Public Data
Map It Anywhere (MIA): Empowering Bird's Eye View Mapping using Large-scale Public Data Open
Top-down Bird's Eye View (BEV) maps are a popular representation for ground robot navigation due to their richness and flexibility for downstream tasks. While recent methods have shown promise for predicting BEV maps from First-Person View…
View article: Flying Calligrapher: Contact-Aware Motion and Force Planning and Control for Aerial Manipulation
Flying Calligrapher: Contact-Aware Motion and Force Planning and Control for Aerial Manipulation Open
Aerial manipulation has gained interest in completing high-altitude tasks that are challenging for human workers, such as contact inspection and defect detection, etc. Previous research has focused on maintaining static contact points or f…
View article: How is the Pilot Doing: VTOL Pilot Workload Estimation by Multimodal Machine Learning on Psycho-physiological Signals
How is the Pilot Doing: VTOL Pilot Workload Estimation by Multimodal Machine Learning on Psycho-physiological Signals Open
Vertical take-off and landing (VTOL) aircraft do not require a prolonged runway, thus allowing them to land almost anywhere. In recent years, their flexibility has made them popular in development, research, and operation. When compared to…
View article: UniSaT: Unified-Objective Belief Model and Planner to Search for and Track Multiple Objects
UniSaT: Unified-Objective Belief Model and Planner to Search for and Track Multiple Objects Open
Path planning for autonomous search and tracking of multiple objects is a critical problem in applications such as reconnaissance, surveillance, and data gathering. Due to the inherent competing objectives of searching for new objects whil…
View article: RuleFuser: An Evidential Bayes Approach for Rule Injection in Imitation Learned Planners and Predictors for Robustness under Distribution Shifts
RuleFuser: An Evidential Bayes Approach for Rule Injection in Imitation Learned Planners and Predictors for Robustness under Distribution Shifts Open
Modern motion planners for autonomous driving frequently use imitation learning (IL) to draw from expert driving logs. Although IL benefits from its ability to glean nuanced and multi-modal human driving behaviors from large datasets, the …