Safe path planning for UAV urban operation under GNSS signal occlusion risk

Delamer, Jean-Alexis; Watanabe, Yoko; Chanel, Caroline Ponzoni Carvalho

doi:10.1016/j.robot.2021.103800

Cited by 25 publications

(33 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The original planning model, proposed by [1], is formalized as a Mixed-Observability Markov Decision Process (MOMDP) [7], a special class of the POMDP framework. The state space is factorized into fully and partially observable state variables, respectively denoted by s v and s h , what reduces the belief state space dimension, and in turn, reduces policy computation time.…”

Section: Uav Urban Navigation Pomdp-based Problemmentioning

confidence: 99%

“…Given the satellite geometry, user location and surrounding environment, a PDOP map is generated by using a GNSS simulator. We assume PDOP value to follow a zero-mean Gaussian distribution [1]. Then, the PDOP map is transformed into a probability map of GNSS availability by setting a maximum position error threshold ε:…”

Section: Feature Vectorsmentioning

confidence: 99%

“…In the following, we describe the settings used in our experiments. The GNC model and the reference velocity settings are the same as those described in [1].…”

Section: Settingsmentioning

confidence: 99%

“…In an urban environment, the GNSS satellites can be masked by the buildings surrounding the UAV, the accuracy or even the availability of the measured position can then be significantly altered, what can lead to a fatal collision. [1] formalize the UAV urban navigation problem under uncertain GNSS availability as a Partially Observable Markov Decision Process (POMDP) [2]. The latter is a principled approach to solve planning problems under uncertainty.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Learning Path Constraints for UAV Autonomous Navigation Under Uncertain GNSS Availability

et al. 2022

Self Cite

View full text Add to dashboard Cite

This paper addresses a safe path planning problem for UAV urban navigation, under uncertain GNSS availability. The problem can be modeled as a POMDP and solved with sampling-based algorithms. However, such a complex domain suffers from high computational cost and achieves poor results under real-time constraints. Recent research seeks to integrate offline learning in order to efficiently guide online planning. Inspired by the state-of-the-art CAMP (Context-specific Abstract Markov decision Process) formalization, this paper proposes an offline process which learns the path constraint to impose during online POMDP solving in order to reduce the policy search space. More precisely, the offline learnt constraint selector returns the best path constraint according to the GNSS availability probability in the environment. Conclusions of experiments, carried out for three environments, show that using the proposed approach allows to improve the quality of a solution reached by an online planner, within a fixed decision-making timeframe, particularly when GNSS availability probability is low.

show abstract

Section: Uav Urban Navigation Pomdp-based Problemmentioning

confidence: 99%

Section: Feature Vectorsmentioning

confidence: 99%

“…In the following, we describe the settings used in our experiments. The GNC model and the reference velocity settings are the same as those described in [1].…”

Section: Settingsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning Path Constraints for UAV Autonomous Navigation Under Uncertain GNSS Availability

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Due to the intrinsic uncertainty of the robot environment, it is necessary for the goal reasoning process to manage uncertain information. While some automated planning methods allow to manage uncertainty, for instance using contingent approaches [4] or probabilistic planning [5], they manage uncertainties related to the achievement of one objective (or optimizing one utility function), and do not allow to integrate goal reasoning, i.e. the ability to adapt the current objectives according to the situation.…”

Section: Introductionmentioning

confidence: 99%

Autonomous Decision-Making With Incomplete Information and Safety Rules Based on Non-Monotonic Reasoning

Vilchis-Medina

Godary-Dejean

Lesire

2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

In this article we propose a decision process integrating Non-Monotonic Reasoning (NMR), embedded in a deliberative architecture. The NMR process uses Default Logic to implement goal reasoning, managing partially observable or incomplete information, allowing the design of default behaviours completed by the handling of specific situations, in order to manage the current mission objective as well as safety rules. We illustrate our approach through an application of an underwater robot performing a marine biology mission.

show abstract

Robust Q‐learning‐based multi‐objective sheep flock optimizer with a Cauchy operator for effective path planning in unmanned aerial vehicles

Kumar,

Saha

2023

Int J Communication

View full text Add to dashboard Cite

SummaryUnmanned aerial vehicle (UAV) path planning can be treated as a nondeterministic polynomial (NP) hard concern or an optimization problem. The conventional approaches are unable to effectively handle these issues due to discontinuity, non‐linearity, multi‐modality, and inseparability. On the other hand, meta‐heuristic algorithms are effective at tackling these issues because they are simple, adaptable, and derivation free. To enhance the performance in a variety of challenging circumstances, this paper proposes a novel Q‐learning‐based multi‐objective sheep flock optimizer with a Cauchy operator (Q‐MOSFO‐CA) to solve the constrained UAV path planning issues. The multi‐objective functions considered here are costs and constraints (threat, terrain, turning, climbing, and gliding constraints) to determine the feasible and optimal path. To avoid the probability of falling into the local optimum and to address the shortcoming of unbalanced convergence and also to maintain the exploitation and exploration capability, the Cauchy operator (CA) is integrated with the sheep flock optimization (SFO) algorithm. The Q‐learning model is introduced to balance both the global and local searches. Here, the exploration model performs the global search whereas the exploitation model performs the local search to attain an optimal solution. In the simulation scenario, the statistical analysis is conducted under two scenarios, and some essential measures such as the number of iterations at convergence (NIC), evaluation time (ET), energy consumption, and convergence analysis are determined. The proposed method obtains NIC of 1305 and 1436, ET of 12.8 and 15.2 s, and energy consumption of 20,600 and 21,465 J for both Scenarios 1 and 2, respectively.

show abstract

Safe path planning for UAV urban operation under GNSS signal occlusion risk

Cited by 25 publications

References 30 publications

Learning Path Constraints for UAV Autonomous Navigation Under Uncertain GNSS Availability

Learning Path Constraints for UAV Autonomous Navigation Under Uncertain GNSS Availability

Autonomous Decision-Making With Incomplete Information and Safety Rules Based on Non-Monotonic Reasoning

Robust Q‐learning‐based multi‐objective sheep flock optimizer with a Cauchy operator for effective path planning in unmanned aerial vehicles

Contact Info

Product

Resources

About