You Only Crash Once: Improved Object Detection for Real-Time, Sim-to-Real Hazardous Terrain Detection and Classification for Autonomous Planetary Landings

• URL: http://arxiv.org/abs/2303.04891v1
• Date: Wed, 8 Mar 2023 21:11:51 GMT
• Title: You Only Crash Once: Improved Object Detection for Real-Time, Sim-to-Real Hazardous Terrain Detection and Classification for Autonomous Planetary Landings
• Authors: Timothy Chase Jr, Chris Gnam, John Crassidis, Karthik Dantu
• Abstract summary: A cheap and effective way of detecting hazardous terrain is through the use of visual cameras. Traditional techniques for visual hazardous terrain detection focus on template matching and registration to pre-built hazard maps. We introduce You Only Crash Once (YOCO), a deep learning-based visual hazardous terrain detection and classification technique.
• Score: 7.201292864036088
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The detection of hazardous terrain during the planetary landing of spacecraft plays a critical role in assuring vehicle safety and mission success. A cheap and effective way of detecting hazardous terrain is through the use of visual cameras, which ensure operational ability from atmospheric entry through touchdown. Plagued by resource constraints and limited computational power, traditional techniques for visual hazardous terrain detection focus on template matching and registration to pre-built hazard maps. Although successful on previous missions, this approach is restricted to the specificity of the templates and limited by the fidelity of the underlying hazard map, which both require extensive pre-flight cost and effort to obtain and develop. Terrestrial systems that perform a similar task in applications such as autonomous driving utilize state-of-the-art deep learning techniques to successfully localize and classify navigation hazards. Advancements in spacecraft co-processors aimed at accelerating deep learning inference enable the application of these methods in space for the first time. In this work, we introduce You Only Crash Once (YOCO), a deep learning-based visual hazardous terrain detection and classification technique for autonomous spacecraft planetary landings. Through the use of unsupervised domain adaptation we tailor YOCO for training by simulation, removing the need for real-world annotated data and expensive mission surveying phases. We further improve the transfer of representative terrain knowledge between simulation and the real world through visual similarity clustering. We demonstrate the utility of YOCO through a series of terrestrial and extraterrestrial simulation-to-real experiments and show substantial improvements toward the ability to both detect and accurately classify instances of planetary terrain.

Related papers

• RLaGA: A Reinforcement Learning Augmented Genetic Algorithm For Searching Real and Diverse Marker-Based Landing Violations [0.7709288517758135]
  It's important to fully test auto-landing systems before deploying them in the real-world to ensure safety. This paper proposes RLaGA, a reinforcement learning (RL) augmented search-based testing framework. Our method generates up to 22.19% more violation cases and nearly doubles the diversity of generated violation cases.
  arXiv  Detail & Related papers  (2023-10-11T10:54:01Z)
• Efficient Real-time Smoke Filtration with 3D LiDAR for Search and Rescue with Autonomous Heterogeneous Robotic Systems [56.838297900091426]
  Smoke and dust affect the performance of any mobile robotic platform due to their reliance on onboard perception systems. This paper proposes a novel modular computation filtration pipeline based on intensity and spatial information.
  arXiv  Detail & Related papers  (2023-08-14T16:48:57Z)
• Language-Guided 3D Object Detection in Point Cloud for Autonomous Driving [91.91552963872596]
  We propose a new multi-modal visual grounding task, termed LiDAR Grounding. It jointly learns the LiDAR-based object detector with the language features and predicts the targeted region directly from the detector. Our work offers a deeper insight into the LiDAR-based grounding task and we expect it presents a promising direction for the autonomous driving community.
  arXiv  Detail & Related papers  (2023-05-25T06:22:10Z)
• SpaceYOLO: A Human-Inspired Model for Real-time, On-board Spacecraft Feature Detection [0.0]
  Real-time, automated spacecraft feature recognition is needed to pinpoint the locations of collision hazards. New algorithm SpaceYOLO fuses a state-of-the-art object detector YOLOv5 with a separate neural network based on human-inspired decision processes. Performance in autonomous spacecraft detection of SpaceYOLO is compared to ordinary YOLOv5 in hardware-in-the-loop experiments.
  arXiv  Detail & Related papers  (2023-02-02T02:11:39Z)
• Deep Monocular Hazard Detection for Safe Small Body Landing [12.922946578413578]
  Hazard detection and avoidance is a key technology for future robotic small body sample return and lander missions. We propose a novel safety mapping paradigm that leverages deep semantic segmentation techniques to predict landing safety directly from a single monocular image. We demonstrate precise and accurate safety mapping performance on real in-situ imagery of prospective sample sites from the OSIRIS-REx mission.
  arXiv  Detail & Related papers  (2023-01-30T19:40:46Z)
• Aerial View Goal Localization with Reinforcement Learning [6.165163123577484]
  We present a framework that emulates a search-and-rescue (SAR)-like setup without requiring access to actual UAVs. In this framework, an agent operates on top of an aerial image (proxy for a search area) and is tasked with localizing a goal that is described in terms of visual cues. We propose AiRLoc, a reinforcement learning (RL)-based model that decouples exploration (searching for distant goals) and exploitation (localizing nearby goals)
  arXiv  Detail & Related papers  (2022-09-08T10:27:53Z)
• Detection and Initial Assessment of Lunar Landing Sites Using Neural Networks [0.0]
  This paper will focus on a passive autonomous hazard detection and avoidance sub-system to generate an initial assessment of possible landing regions for the guidance system. The system uses a single camera and the MobileNetV2 neural network architecture to detect and discern between safe landing sites and hazards such as rocks, shadows, and craters.
  arXiv  Detail & Related papers  (2022-07-23T04:29:18Z)
• Embedding Earth: Self-supervised contrastive pre-training for dense land cover classification [61.44538721707377]
  We present Embedding Earth a self-supervised contrastive pre-training method for leveraging the large availability of satellite imagery. We observe significant improvements up to 25% absolute mIoU when pre-trained with our proposed method. We find that learnt features can generalize between disparate regions opening up the possibility of using the proposed pre-training scheme.
  arXiv  Detail & Related papers  (2022-03-11T16:14:14Z)
• Towards Robust Monocular Visual Odometry for Flying Robots on Planetary Missions [49.79068659889639]
  Ingenuity, that just landed on Mars, will mark the beginning of a new era of exploration unhindered by traversability. We present an advanced robust monocular odometry algorithm that uses efficient optical flow tracking. We also present a novel approach to estimate the current risk of scale drift based on a principal component analysis of the relative translation information matrix.
  arXiv  Detail & Related papers  (2021-09-12T12:52:20Z)
• Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation [62.22058066456076]
  Reinforcement Learning (RL) represents powerful tools to solve complex robotic tasks. RL does not work directly in the real-world, which is known as the sim-to-real transfer problem. We propose a method that learns on an observation space constructed by point clouds and environment randomization.
  arXiv  Detail & Related papers  (2020-07-27T17:46:59Z)
• Learning to Move with Affordance Maps [57.198806691838364]
  The ability to autonomously explore and navigate a physical space is a fundamental requirement for virtually any mobile autonomous agent. Traditional SLAM-based approaches for exploration and navigation largely focus on leveraging scene geometry. We show that learned affordance maps can be used to augment traditional approaches for both exploration and navigation, providing significant improvements in performance.
  arXiv  Detail & Related papers  (2020-01-08T04:05:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.