Gaussian Process-based Learning Control of Aerial Robots for Precise Visualization of Geological Outcrops

Mehndiratta, Mohit; Kayacan, Erdal

doi:10.23919/ecc51009.2020.9143655

Cited by 24 publications

(14 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Related Workmentioning

confidence: 91%

“…Similar to our work, in [11,12,[29][30][31], the authors use Gaussian Processes to improve the control performance of a robotic platform. In [29], Gaussian Processes are used on a quadrotor to correct for wind disturbances. Since instead of platform states only observed disturbances are fed to the GPs, this approach does not learn a dynamics model and can only react to disturbances once they have been observed.…”

Section: Related Workmentioning

confidence: 91%

“…Our work is inspired by these approaches, but extends [11,12] to three-dimensional GP predictions for the quadrotor platform. Instead of learning a mapping from observed disturbances to future disturbance as in [29], we focus on fast flight and correct for aerodynamic effects that arise due to the fast ego-motion of the platform. We tightly integrate the predictions of the Gaussian Processes into the MPC formulation.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Data-Driven MPC for Quadrotors

Torrente

Kaufmann

Fohn

et al. 2021

IEEE Robot. Autom. Lett.

193

139

View full text Add to dashboard Cite

Aerodynamic forces render accurate high-speed trajectory tracking with quadrotors extremely challenging. These complex aerodynamic effects become a significant disturbance at high speeds, introducing large positional tracking errors, and are extremely difficult to model. To fly at high speeds, feedback control must be able to account for these aerodynamic effects in real-time. This necessitates a modeling procedure that is both accurate and efficient to evaluate. Therefore, we present an approach to model aerodynamic effects using Gaussian Processes, which we incorporate into a Model Predictive Controller to achieve efficient and precise real-time feedback control, leading to up to 70% reduction in trajectory tracking error at high speeds. We verify our method by extensive comparison to a state-of-theart linear drag model in synthetic and real-world experiments at speeds of up to 14m/s and accelerations beyond 4g. SUPPLEMENTARY MATERIALVideo: https://youtu.be/FHvDghUUQtc Code: https://github.com/uzh-rpg/data driven mpc I. INTRODUCTIONAccurate trajectory tracking with quadrotors in high-speed and high-acceleration regimes is still a challenging research problem. While autonomous quadrotors have seen a significant gain in popularity and have been applied in a variety of industries ranging from agriculture to transport, security, infrastructure, entertainment, and search and rescue, they still do not exploit their full maneuverability. The ability to precisely control drones during fast and highly agile maneuvers would allow to not only fly fast in known-free environments, but also close to obstacles, humans, or through openings, where already small deviations from the reference have catastrophic consequences.Operating a quadrotor at high speeds and controlling it through agile, high-acceleration maneuvers requires to account for complex aerodynamic effects acting on the platform. These effects are difficult to model, since they consist of a combination of propeller lift and drag dependent on the induced airstream velocity, fuselage drag, and complex or even turbulent effects due to the interaction between the propellers, the downwash of other propellers, and the fuselage.

show abstract

Section: Related Workmentioning

confidence: 91%

Section: Related Workmentioning

confidence: 91%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Data-Driven MPC for Quadrotors

Torrente

Kaufmann

Fohn

et al. 2021

IEEE Robot. Autom. Lett.

193

139

View full text Add to dashboard Cite

show abstract

“…Keeping in mind the nonlinear and constrained nature of the control problem, (N)MPC is a viable candidate. Over other model-based control approaches, it has been remarkably successful in control and planning of numerous robotic platforms and tasks, including: (i) ground and aerial robots in [26]- [28], (ii) aerial manipulation tasks in [29], [30], and (iii) aerial operations under uncertain conditions in [31], [32]. The underlying reason for this success is its unique ability to simultaneously handle constraints and optimize performance through recursive online optimization.…”

Section: B Control Techniquesmentioning

confidence: 99%

QuadPlus: Design, Modeling, and Receding-Horizon-Based Control of a Hyperdynamic Quadrotor

Singh

Mehndiratta²,

Feroskhan

2022

IEEE Trans. Aerosp. Electron. Syst.

Self Cite

View full text Add to dashboard Cite

“…The model predictive controller (MPC) has shown remarkable success for the control and planning of numerous robotic systems [1][2][3][4][5][6][7][8][9][10][11][12][13][14]. However, its design necessitates an inevitable tuning procedure that involves the determination of its cost function weights.…”

Section: Introductionmentioning

confidence: 99%

Can Deep Models Help a Robot to Tune Its Controller? A Step Closer to Self-Tuning Model Predictive Controllers

2021

Self Cite

View full text Add to dashboard Cite

Motivated by the difficulty roboticists experience while tuning model predictive controllers (MPCs), we present an automated weight set tuning framework in this work. The enticing feature of the proposed methodology is the active exploration approach that adopts the exploration–exploitation concept at its core. Essentially, it extends the trial-and-error method by benefiting from the retrospective knowledge gained in previous trials, thereby resulting in a faster tuning procedure. Moreover, the tuning framework adopts a deep neural network (DNN)-based robot model to conduct the trials during the simulation tuning phase. Thanks to its high fidelity dynamics representation, a seamless sim-to-real transition is demonstrated. We compare the proposed approach with the customary manual tuning procedure through a user study wherein the users inadvertently apply various tuning methodologies based on their progressive experience with the robot. The results manifest that the proposed methodology provides a safe and time-saving framework over the manual tuning of MPC by resulting in flight-worthy weights in less than half the time. Moreover, this is the first work that presents a complete tuning framework extending from robot modeling to directly obtaining the flight-worthy weight sets to the best of the authors’ knowledge.

show abstract

Gaussian Process-based Learning Control of Aerial Robots for Precise Visualization of Geological Outcrops

Cited by 24 publications

References 15 publications

Data-Driven MPC for Quadrotors

Data-Driven MPC for Quadrotors

QuadPlus: Design, Modeling, and Receding-Horizon-Based Control of a Hyperdynamic Quadrotor

Can Deep Models Help a Robot to Tune Its Controller? A Step Closer to Self-Tuning Model Predictive Controllers

Contact Info

Product

Resources

About