Competency-Aware Planning for Probabilistically Safe Navigation Under Perception Uncertainty
Not on the map. Why?
Abstract (arXiv)
Perception-based navigation systems are useful for unmanned ground vehicle (UGV) navigation in complex terrains, where traditional depth-based navigation schemes are insufficient. However, these data-driven methods are highly dependent on their training data and can fail in surprising and dramatic ways with little warning. To ensure the safety of the vehicle and the surrounding environment, it is imperative that the navigation system is able to recognize the predictive uncertainty of the perception model and respond safely and effectively in the face of uncertainty. In an effort to enable safe navigation under perception uncertainty, we develop a probabilistic and reconstruction-based competency estimation (PaRCE) method to estimate the model's level of familiarity with an input image as a whole and with specific regions in the image. We find that the overall competency score can correctly predict correctly classified, misclassified, and out-of-distribution (OOD) samples. We also confirm that the regional competency maps can accurately distinguish between familiar and unfamiliar regions across images. We then use this competency information to develop a planning and control scheme that enables effective navigation while maintaining a low probability of error. We find that the competency-aware scheme greatly reduces the number of collisions with unfamiliar obstacles, compared to a baseline controller with no competency awareness. Furthermore, the regional competency information is very valuable in enabling efficient navigation.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 45 of its 71 references that are in the map. First posted on arXiv 9 Sep 2024.
Builds on
45 of 71 references.
References · 45
- 2017On Calibration of Modern Neural Networkscited by 4,860
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
- 2015Variational Inference with Normalizing Flowscited by 2,161
- 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
- 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
- 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
- 2020Energy-based Out-of-distribution Detectioncited by 1,296
- 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
- 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
- 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
- 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
33 more
- 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
- 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
- 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
- 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
- 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
- 2015Towards Open Set Deep Networkscited by 533
- 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
- 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
- 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
- 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
- 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
- 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
- 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
- 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
- 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 263
- 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 225
- 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
- 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
- 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
- 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
- 2021Student-Teacher Feature Pyramid Matching for Anomaly Detectioncited by 145
- 2018Efficient GAN-Based Anomaly Detectioncited by 122
- 2022Anomalib: A Deep Learning Library for Anomaly Detectioncited by 75
- 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 67
- 2021Anomaly Detection in Medical Imaging -- A Mini Reviewcited by 44
- 2022ScaTE: A Scalable Framework for Self-Supervised Traversability Estimation in Unstructured Environmentscited by 21
- 2023Learning Risk-Aware Costmaps via Inverse Reinforcement Learning for Off-Road Navigationcited by 15
- 2022Motion Primitives-based Navigation Planning using Deep Collision Predictioncited by 6
- 2019Justification-Based Reliability in Machine Learningcited by 5
- 2023Safe Navigation in Unstructured Environments by Minimizing Uncertainty in Control and Perceptioncited by 5
- 2023Uncertainty-aware hybrid paradigm of nonlinear MPC and model-based RL for offroad navigation: Exploration of transformers in the predictive modelcited by 3
- 2021Improving Robustness of Deep Neural Networks for Aerial Navigation by Incorporating Input Uncertaintycited by 2
- 2022Quantifying and Using System Uncertainty in UAV Navigationcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.