VeloBins: Learning Velocity and Its Uncertainty via Bins and Error-Conditioned Gaussian Labels for Aerial Inertial Odometry

• URL: http://arxiv.org/abs/2608.29720v1
• Date: Sun, 30 Aug 2026 11:00:45 GMT
• Title: VeloBins: Learning Velocity and Its Uncertainty via Bins and Error-Conditioned Gaussian Labels for Aerial Inertial Odometry
• Abstract summary: Inertial odometry is critical for aerial robots, where aggressive maneuvers and poor lighting degrade visual sensors.<n>We introduce VeloBins, which reformulates velocity regression as classification over discretized velocity bins.<n>We evaluate VeloBins on four aerial datasets, ranging from free-form aggressive flights and a 27 g nano-quadrotor to drone racing at over 21m/s.
• Score: 5.366057870797728
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Inertial odometry (IO) is critical for aerial robots, where aggressive maneuvers and poor lighting degrade visual sensors. Recent learning-based IO methods improve traditional integration-based approaches by learning motion priors from IMU and platform-specific sensors, then fusing the predictions within an extended Kalman filter. However, learning velocity through regression is difficult, while jointly estimating uncertainty with a separate decoder and negative log-likelihood (NLL) loss further complicates training and can lead to over-confident estimates. We introduce VeloBins, which reformulates velocity regression as classification over discretized velocity bins. We decode both the velocity from the bin distribution's expectation and the uncertainty from its variance, removing the need for a separate uncertainty decoder. We further supervise the uncertainty explicitly using an error-conditioned Gaussian label centered at the ground-truth velocity, with a standard deviation set to the velocity error. We evaluate VeloBins on four aerial datasets, ranging from free-form aggressive flights and a 27 g nano-quadrotor to drone racing at over 21~m/s. VeloBins achieves the lowest average errors on all four datasets, reducing velocity, relative trajectory, and absolute trajectory errors by 3-27%, 8-40%, and 6-53%, respectively, compared with the strongest baseline. Notably, the proposed supervision achieves the lowest NLL and best filter consistency despite never optimizing an NLL loss. The code will be available upon acceptance.

Related papers

• Dense Soft Weighting for Radar Ego-Velocity Estimation [6.356174487225252]
  We present Dense Soft Weighting, an analytic radar front-end for ego-velocity estimation.<n>It maps every range-Doppler cell to a continuous confidence metric rather than enforcing a binary detection threshold.<n>It reduces mean absolute pose error by 31-45% relative to the strongest CFAR point-cloud baseline.
  arXiv  Detail & Related papers  (2026-07-29T14:37:52Z)
• DINS-IO: Learned Inertial Odometry via Differentiable INS Consistency [10.120588097901377]
  We propose DINS-IO, which learns inertial odometry directly from raw IMU streams without position labels.<n>We cast this constraint as a sliding-window least-squares problem with a globally shared bias, solve it in closed form, and use the solver residual as a self-supervised loss.<n>Since the self-supervised network learns consistent motion but its velocity is not yet metrically calibrated, we calibrate it to true metric velocity from a few labeled trajectories.
  arXiv  Detail & Related papers  (2026-07-22T14:52:28Z)
• Trajectory-Consistent Flow Matching for Robust Visuomotor Policy Learning [1.7616042687330642]
  Flow matching policies learn continuous velocity fields that transport noise to actions, enabling deterministic inference for robot manipulation.<n>Standard training optimize a pointwise velocity objective while inference requires numerical integration of that field -- a mismatch that causes compounding trajectory errors.<n>We propose four complementary remedies: (1) auxiliary rectified flow velocity regression that provides uniform temporal supervision across the full time interval; (2) multi-step trajectory consistency training that supervises the integrated displacement of the velocity field over trajectory segments; and (3) velocity field regularization that enforces temporal smoothness.
  arXiv  Detail & Related papers  (2026-05-08T21:44:10Z)
• UNRIO: Uncertainty-Aware Velocity Learning for Radar-Inertial Odometry [16.577608323279662]
  UNRIO is an uncertainty-aware radar-inertial odometry system.<n>It estimates ego-velocity directly from raw mmWave radar IQ signals.
  arXiv  Detail & Related papers  (2026-04-15T07:43:06Z)
• MeanFlow Transformers with Representation Autoencoders [71.45823902973349]
  MeanFlow (MF) is a diffusion-motivated generative model that enables efficient few-step generation by learning long jumps directly from noise to data.<n>We develop an efficient training and sampling scheme for MF in the latent space of a Representation Autoencoder (RAE)<n>We achieve a 1-step FID of 2.03, outperforming vanilla MF's 3.43, while reducing sampling GFLOPS by 38% and total training cost by 83% on ImageNet 256.
  arXiv  Detail & Related papers  (2025-11-17T06:17:08Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Full waveform inversion with CNN-based velocity representation extension [4.255346660147713]
  Full waveform inversion (FWI) updates the velocity model by minimizing the discrepancy between observed and simulated data.<n>Discretization errors in numerical modeling and incomplete seismic data acquisition can introduce noise, which propagates through the adjoint operator.<n>We employ a convolutional neural network (CNN) to refine the velocity model before performing the forward simulation.<n>We use the same data misfit loss to update both the velocity and network parameters, thereby forming a self-supervised learning procedure.
  arXiv  Detail & Related papers  (2025-04-22T12:14:38Z)
• Collaborative Learning with a Drone Orchestrator [79.75113006257872]
  A swarm of intelligent wireless devices train a shared neural network model with the help of a drone. The proposed framework achieves a significant speedup in training, leading to an average 24% and 87% saving in the drone hovering time.
  arXiv  Detail & Related papers  (2023-03-03T23:46:25Z)
• Correlating sparse sensing for large-scale traffic speed estimation: A Laplacian-enhanced low-rank tensor kriging approach [76.45949280328838]
  We propose a Laplacian enhanced low-rank tensor (LETC) framework featuring both lowrankness and multi-temporal correlations for large-scale traffic speed kriging. We then design an efficient solution algorithm via several effective numeric techniques to scale up the proposed model to network-wide kriging.
  arXiv  Detail & Related papers  (2022-10-21T07:25:57Z)
• Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models [134.83964935755964]
  In deep learning, different kinds of deep networks typically need different extrapolations, which have to be chosen after multiple trials.<n>To relieve this issue and consistently improve the model training speed deep networks, we propose the ADAtive Nesterov momentum Transformer.
  arXiv  Detail & Related papers  (2022-08-13T16:04:39Z)
• StreamYOLO: Real-time Object Detection for Streaming Perception [84.2559631820007]
  We endow the models with the capacity of predicting the future, significantly improving the results for streaming perception. We consider multiple velocities driving scene and propose Velocity-awared streaming AP (VsAP) to jointly evaluate the accuracy. Our simple method achieves the state-of-the-art performance on Argoverse-HD dataset and improves the sAP and VsAP by 4.7% and 8.2% respectively.
  arXiv  Detail & Related papers  (2022-07-21T12:03:02Z)
• Understanding and Mitigating the Tradeoff Between Robustness and Accuracy [88.51943635427709]
  Adversarial training augments the training set with perturbations to improve the robust error. We show that the standard error could increase even when the augmented perturbations have noiseless observations from the optimal linear predictor.
  arXiv  Detail & Related papers  (2020-02-25T08:03:01Z)

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.