Nonlinear System Identification Nano-drone Benchmark

• URL: http://arxiv.org/abs/2512.14450v1
• Date: Tue, 16 Dec 2025 14:37:33 GMT
• Title: Nonlinear System Identification Nano-drone Benchmark
• Abstract summary: We introduce a benchmark for system identification based on 75k real-world samples from the Crazyflie 2.1 Brushless nano-quadrotor.<n>The platform presents a challenging testbed due to its multi-input, multi-output nature, open-loop instability, and nonlinear dynamics under agile maneuvers.
• Score: 4.997595784983579
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce a benchmark for system identification based on 75k real-world samples from the Crazyflie 2.1 Brushless nano-quadrotor, a sub-50g aerial vehicle widely adopted in robotics research. The platform presents a challenging testbed due to its multi-input, multi-output nature, open-loop instability, and nonlinear dynamics under agile maneuvers. The dataset comprises four aggressive trajectories with synchronized 4-dimensional motor inputs and 13-dimensional output measurements. To enable fair comparison of identification methods, the benchmark includes a suite of multi-horizon prediction metrics for evaluating both one-step and multi-step error propagation. In addition to the data, we provide a detailed description of the platform and experimental setup, as well as baseline models highlighting the challenge of accurate prediction under real-world noise and actuation nonlinearities. All data, scripts, and reference implementations are released as open-source at https://github.com/idsia-robotics/nanodrone-sysid-benchmark to facilitate transparent comparison of algorithms and support research on agile, miniaturized aerial robotics.

Related papers

• Crazyflow: An Accurate, GPU-Accelerated, Differentiable Drone Simulator in JAX [8.563893272897879]
  Crazyflow is a simulator designed to push the limits of aerial-robotics algorithm development.<n>It achieves speeds more than an order of magnitude faster for a single drone and can simulate thousands of swarms of 4000 drones each.<n>By pushing accuracy, speed, and differentiability simultaneously, Crazyflow serves as an open-source resource for synthetic data generation.
  arXiv  Detail & Related papers  (2026-05-31T22:38:46Z)
• NanoBench: A Multi-Task Benchmark Dataset for Nano-Quadrotor System Identification, Control, and State Estimation [1.0312968200748118]
  Existing aerial-robotics benchmarks target vehicles from hundreds of grams to several kilograms and typically expose only high-level state data.<n>We introduce NanoBench, an open-source multi-task benchmark collected on the commercially available Crazyflie 2.1 nano-quadrotor (takeoff weight 27 g) in a Vicon motion capture arena.<n>The dataset contains over 170 flight trajectories spanning hover, multi-frequency aerodynamics, standard tracking, and aggressive maneuvers across multiple speed regimes.
  arXiv  Detail & Related papers  (2026-03-10T17:01:59Z)
• Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons [69.87766750714945]
  General-purpose robot reward models are typically trained to predict absolute task progress from expert demonstrations.<n>We introduce Robometer, a scalable reward modeling framework that combines intra-trajectory progress supervision with inter-trajectory preference supervision.<n>Robometer is trained with a dual objective: a frame-level progress loss that anchors reward magnitude on expert data, and a trajectory-comparison preference loss that imposes global ordering constraints.
  arXiv  Detail & Related papers  (2026-03-02T17:38:58Z)
• The Mini Wheelbot Dataset: High-Fidelity Data for Robot Learning [11.872449230532501]
  This paper introduces a comprehensive dynamics dataset for the Mini Wheelbot, an open-source, quasi-symmetric balancing reaction wheel unicycle.<n>The dataset provides 1 kHz synchronized data encompassing all onboard sensor readings, state estimates, ground-truth poses from a motion capture system, and third-person video logs.
  arXiv  Detail & Related papers  (2026-01-16T16:06:32Z)
• OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value [74.80873109856563]
  OpenDataArena (ODA) is a holistic and open platform designed to benchmark the intrinsic value of post-training data.<n>ODA establishes a comprehensive ecosystem comprising four key pillars: (i) a unified training-evaluation pipeline that ensures fair, open comparisons across diverse models; (ii) a multi-dimensional scoring framework that profiles data quality along tens of distinct axes; and (iii) an interactive data lineage explorer to visualize dataset genealogy and dissect component sources.
  arXiv  Detail & Related papers  (2025-12-16T03:33:24Z)
• X-IONet: Cross-Platform Inertial Odometry Network with Dual-Stage Attention [6.545488752368577]
  X-IONet is a cross-platform inertial odometry framework that operates solely using a single Inertial Measurement Unit (IMU)<n>It incorporates a rule-based expert selection module to classify motion platforms and route IMU sequences to platform-specific expert networks.<n>X-IONet achieves state-of-the-art performance, reducing Absolute Trajectory Error (ATE) by 14.3% and Relative Trajectory Error (RTE) by 11.4% on pedestrian data.
  arXiv  Detail & Related papers  (2025-11-11T14:06:52Z)
• Towards Vision Mixture of Experts for Wildlife Monitoring on the Edge [13.112893692624768]
  TinyML' community is actively proposing methods to save communication bandwidth and excessive cloud storage costs. We explore similar per patch conditional computation for the first time for mobile vision transformers. We evaluate the model on Cornell Sap Sucker Woods 60, a fine grained bird species discrimination dataset.
  arXiv  Detail & Related papers  (2024-11-12T14:36:06Z)
• 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)
• Ultra-low Power Deep Learning-based Monocular Relative Localization Onboard Nano-quadrotors [64.68349896377629]
  This work presents a novel autonomous end-to-end system that addresses the monocular relative localization, through deep neural networks (DNNs), of two peer nano-drones. To cope with the ultra-constrained nano-drone platform, we propose a vertically-integrated framework, including dataset augmentation, quantization, and system optimizations. Experimental results show that our DNN can precisely localize a 10cm-size target nano-drone by employing only low-resolution monochrome images, up to 2m distance.
  arXiv  Detail & Related papers  (2023-03-03T14:14:08Z)
• Certified data-driven physics-informed greedy auto-encoder simulator [0.5249805590164902]
  An auto-encoder and dynamics identification models are trained interactively to discover intrinsic and simple latent-space dynamics. An adaptive greedy sampling algorithm integrated with a physics-informed error indicator is introduced to search for optimal training samples on the fly. Numerical results demonstrate that the proposed method achieves parametric 121 to 2,658x speed-up with 1 to 5% relative errors for radial advection and 2D Burgers dynamical problems.
  arXiv  Detail & Related papers  (2022-11-24T16:22:51Z)
• Inertial Hallucinations -- When Wearable Inertial Devices Start Seeing Things [82.15959827765325]
  We propose a novel approach to multimodal sensor fusion for Ambient Assisted Living (AAL) We address two major shortcomings of standard multimodal approaches, limited area coverage and reduced reliability. Our new framework fuses the concept of modality hallucination with triplet learning to train a model with different modalities to handle missing sensors at inference time.
  arXiv  Detail & Related papers  (2022-07-14T10:04:18Z)
• SUOD: Accelerating Large-Scale Unsupervised Heterogeneous Outlier Detection [63.253850875265115]
  Outlier detection (OD) is a key machine learning (ML) task for identifying abnormal objects from general samples. We propose a modular acceleration system, called SUOD, to address it.
  arXiv  Detail & Related papers  (2020-03-11T00:22:50Z)

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.