Full STEAM ahead: Exactly sparse gaussian process regression for batch continuous-time trajectory estimation on SE(3)

Anderson, Sean; Barfoot, Timothy D.

doi:10.1109/iros.2015.7353368

Cited by 77 publications

(102 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A probabilistic approach for continuous state estimation is presented in [13]. In this method, the use of computationally efficient GP regression over a discrete maximum a posteriori estimation allows the state variables to be queried at any point in time.…”

Section: Related Workmentioning

confidence: 99%

IN2LAMA: INertial Lidar Localisation And MApping

Gentil

Vidal-Calleja

Huang

2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

In this paper, we present INertial Lidar Localisation Autocalibration And MApping (IN2LAAMA): a probabilistic framework for localisation, mapping, and extrinsic calibration based on a 3D-lidar and a 6-DoF-IMU. Most of today's lidars collect geometric information about the surrounding environment by sweeping lasers across their field of view. Consequently, 3Dpoints in one lidar scan are acquired at different timestamps. If the sensor trajectory is not accurately known, the scans are affected by the phenomenon known as motion distortion. The proposed method leverages preintegration with a continuous representation of the inertial measurements to characterise the system's motion at any point in time. It enables precise correction of the motion distortion without relying on any explicit motion model. The system's pose, velocity, biases, and time-shift are estimated via a full batch optimisation that includes automatically generated loop-closure constraints. The autcalibration and the registration of lidar data relies on planar and edge features matched across pairs of scans. The performance of the framework is validated through simulated and real-data experiments.

show abstract

Section: Related Workmentioning

confidence: 99%

IN2LAMA: INertial Lidar Localisation And MApping

Gentil

Vidal-Calleja

Huang

2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

show abstract

“…In the remainder of this section we describe the factor graph formulation of and relationship between Smoothing and Mapping (SAM) [6], Simultaneous Trajectory Estimation and Mapping (STEAM) [5,2], Gaussian Process Motion Planning 2 (GPMP2) [7], Simultaneous Localization and Planning (SLAP) [25,1], and our proposed method, Simultaneous Trajectory Estimation and Planning (STEAP). We then provide details on the factors used in the STEAP problem, discuss incremental inference and summarize the STEAP approach with a simple toy example.…”

Section: Simultaneous Trajectory Estimation and Planning With Famentioning

confidence: 99%

“…where f prior is the prior on the first state f prior = f prior (θ 0 ), and f meas is the likelihood of all sensor measurements, which itself factors as Like SAM, Simultaneous trajectory estimation and mapping (STEAM) [5,2] addresses trajectory estimation problems. The key difference is that in STEAM, the trajectory is no longer treated as a discrete sequence of states Θ, but rather a continuous-time trajectory sampled from a GP.…”

Section: A Factorization In Related Problemsmentioning

confidence: 99%

“…2 (c)). GP priors have also been formulated with non-linear SDEs [3] and on the SE(3) Lie group [2].…”

Section: Steap Factor Definitionsmentioning

confidence: 99%

“…This allows us to avoid resolving the STEAP problem from scratch as new observations are encountered and only update the trajectory where required, dramatically reducing the overall computational burden of our approach and enabling a faster-than-realtime solution. To better accommodate mobile manipulation problems, we build on Barfoot et al's recent work on continuous-time trajectory estimation on SE(3) [2] and extend Dong et al [7] to plan trajectories on Lie groups. Finally, we implement our probabilistic inference framework for solving the STEAP problem on the Vector mobile manipulator (Fig.…”

Section: Introduction and Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Simultaneous Trajectory Estimation and Planning via Probabilistic Inference

Mukadam

Dong

Dellaert

et al. 2017

Robotics: Science and Systems XIII

View full text Add to dashboard Cite

Abstract-We provide a unified probabilistic framework for trajectory estimation and planning. The key idea is to view these two problems, usually considered separately, as a single problem. At each time-step the robot is tasked with finding the complete continuous-time trajectory from start to goal. This can be quite difficult; the robot must contend with a potentially high-degreeof-freedom (DOF) trajectory space, uncertainty due to limited sensing capabilities, model inaccuracy, and the stochastic effect of executing actions, and the robot must find the solution in (faster than) real time. To overcome these challenges, we build on recent probabilistic inference approaches to continuous-time localization and mapping and continuous-time motion planning. We solve the joint problem by iteratively recomputing the maximum a posteriori trajectory conditioned on all available sensor data and cost information. Finally, we evaluate our framework empirically in both simulation and on a mobile manipulator. I. INTRODUCTION & RELATED WORKTrajectory estimation and planning are both important capabilities for autonomous robot navigation. Trajectory estimation is fundamentally backward-looking: the robot estimates a trajectory of previous states that are consistent with a history of noisy and incomplete sensor data. Conversely, planning is fundamentally forward looking: starting from an estimate of its current state, the robot optimizes a trajectory of future states to minimize a cost function and achieve a feasible solution.In this paper, we provide a unified approach to trajectory estimation and planning. The key idea is to view these two problems, usually considered separately, as a single problem. At each time-step the robot is tasked with finding the complete continuous-time trajectory from start to goal. This can be quite difficult; the robot must contend with a potentially highdegree-of-freedom (DOF) trajectory space, uncertainty due to limited sensing capabilities, model inaccuracy, and the stochastic effect of executing actions, and the robot must find the solution in (faster than) real time.To overcome these challenges, we build on recent probabilistic inference approaches to continuous-time localization and mapping and continuous-time motion planning. We solve the joint problem by iteratively recomputing the maximum a posteriori (MAP) trajectory conditioned on all available sensor data and cost information. In brief, we represent continuoustime trajectories as samples from a Gaussian process (GP) [5,22] and then formulate the estimation and planning problem on a single probabilistic graphical model. We perform inference on the graph using numerical tools that solve a nonlinear least squares optimization problem, and generate fast, iterative solutions by exploiting the structure of the problem.

show abstract

Point‐LIO: Robust High‐Bandwidth Light Detection and Ranging Inertial Odometry

Wei

Chen

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

Herein, point light detection and ranging inertial odometry (LIO) is presented: a robust and high‐bandwidth light detection and ranging (LiDAR) inertial odometry with the capability to estimate extremely aggressive robotic motions. Point‐LIO has two key novelties. The first one is a point‐by‐point LIO framework that updates the state at each LiDAR point measurement. This framework allows an extremely high‐frequency odometry output, significantly increases the odometry bandwidth, and fundamentally removes the artificial in‐frame motion distortion. The second one is a stochastic process‐augmented kinematic model which models the IMU measurement as an output. This new modeling method enables accurate localization and reliable mapping for aggressive motions even with inertial measurement unit (IMU) measurements saturated in the middle of the motion. Various real‐world experiments are conducted for performance evaluation. Overall, Point‐LIO is capable to provide accurate, high‐frequency odometry (4–8 kHz) and reliable mapping under severe vibrations and aggressive motions with high angular velocity (75 rad s−1) beyond the IMU measuring ranges. Furthermore, an exhaustive benchmark comparison is conducted. Point‐LIO achieves consistently comparable accuracy and time consumption. Finally, two example applications of Point‐LIO are demonstrated, one is a racing drone and the other is a self‐rotating unmanned aerial vehicle, both have aggressive motions.

show abstract

Full STEAM ahead: Exactly sparse gaussian process regression for batch continuous-time trajectory estimation on SE(3)

Cited by 77 publications

References 28 publications

IN2LAMA: INertial Lidar Localisation And MApping

IN2LAMA: INertial Lidar Localisation And MApping

Simultaneous Trajectory Estimation and Planning via Probabilistic Inference

Point‐LIO: Robust High‐Bandwidth Light Detection and Ranging Inertial Odometry

Contact Info

Product

Resources

About