pith. sign in

arxiv: 2411.05516 · v3 · submitted 2024-11-08 · 💻 cs.RO

EROAS: 3D Efficient Reactive Obstacle Avoidance System for Autonomous Underwater Vehicles using 2.5D Forward-Looking Sonar

Pruthviraj Mane , Allen Jacob George , Rajini Makam , Subhash Gurikar , Rudrashis Majumder , Suresh Sundaram This is my paper

Pith reviewed 2026-05-23 17:36 UTC · model grok-4.3

classification 💻 cs.RO
keywords obstacle avoidanceautonomous underwater vehiclesforward-looking sonarcontrol barrier functionsreactive navigation2.5D sensingpartial observability
0
0 comments X

The pith

EROAS augments a 2D forward-looking sonar with pivoting to create on-demand 2.5D sensing and combines gap detection, short-term memory, and safety filters for reactive 3D obstacle avoidance in cluttered underwater environments.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces EROAS, a lightweight framework for AUVs that addresses limited field-of-view and partial observability by adding a pivoting mechanism to a standard 2D sonar. This creates a cost-efficient 2.5D sensor that supplies vertical information only when needed. Three modules work together: SPD2C generates directional commands from sonar profiles, SCG maintains short-term obstacle memory to handle occlusions, and ST-CBF filters commands to keep the vehicle safe. Simulations and hardware-in-the-loop tests show the system produces more efficient paths and fewer collisions than Dynamic Window Approach or Artificial Potential Fields. If the approach holds, AUVs could navigate uncertain 3D spaces with simpler hardware than full 3D sonars require.

Core claim

EROAS augments a 2D FLS with a pivoting mechanism to form a 2.5D sonar that supplies vertical data on demand, then integrates SPD2C for rapid horizontal and vertical gap detection, SCG for short-term spatial memory that compensates for partial views, and ST-CBF to enforce forward-invariant safety constraints, together producing reactive avoidance that improves trajectory efficiency, reduces travel time, and increases safety margins in simulation and HIL tests against DWA and APF baselines.

What carries the argument

The 2.5D sonar formed by pivoting a 2D FLS, together with the SPD2C directional controller, SCG short-term memory buffer, and ST-CBF safety filter.

If this is right

  • The system generates reference commands in both horizontal and vertical planes from 2D sonar profiles.
  • Short-term obstacle memory mitigates effects of turbidity and occlusions during forward motion.
  • Spatio-temporal control barrier functions keep the vehicle inside safe sets while following nominal references.
  • Trajectory efficiency and travel time improve relative to DWA and APF in cluttered 3D scenes.
  • The approach runs on standard 2D hardware without requiring a full 3D sonar array.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Similar pivoting-plus-memory designs could reduce sensor cost in other domains where full 3D sensing is impractical, such as ground robots in fog.
  • Extending the memory buffer with simple motion prediction might further reduce reliance on frequent pivots.
  • If mechanical pivoting proves reliable over long missions, fleets of low-cost AUVs could adopt the same sensing strategy without added weight.

Load-bearing premise

The pivoting mechanism supplies needed vertical information at low cost and the short-term memory buffer compensates for occlusions and partial views.

What would settle it

An experiment in which the AUV encounters a vertically offset obstacle that appears only after the sonar has passed the scan angle, and the memory buffer fails to retain its position, producing a collision despite the safety filter.

Figures

Figures reproduced from arXiv: 2411.05516 by Allen Jacob George, Pruthviraj Mane, Rajini Makam, Rudrashis Majumder, Subhash Gurikar, Suresh Sundaram.

Figure 1
Figure 1. Figure 1: Details of single beam of FLS [33]. where, J(η) is a standard Jacobian matrix. The REXROV2 is assumed to operate with fixed pitch and roll motion, so (1) and (2) can be represented as x˙ v = vx cos ψ − vy sin ψ, y˙v = vx sin ψ + vy cos ψ, z˙v = vz, ψ˙ = r. (3) 2) Sonar Model: The sonar employed in this work is BlueView P900 NPS multibeam sonar. The sonar plugin [33] is deployed in DAVE simulator [31]. The … view at source ↗
Figure 2
Figure 2. Figure 2: AUV navigating in cluttered environment instantaneous distance between the vehicle and any of the obstacle be, d(pv(t), po(t)) = min po∈Po ∥pv(t) − po(t)∥ (6) The AUV needs to reach the goal within a defined tolerance, ε and it should always maintain at least a distance dmin from the obstacles to finally avoid them, as shown in [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Schematic of EROAS framework. The collection of all such subsets forms, G = {G1, G2, . . . , Gk}, k = |BF | − L + 1. (9) Since each Gi spans L consecutive beams, we identify the mid-beam of Gi as bM,i = bi+⌊L/2⌋. The set of all mid-beams is then M = {bM,1, bM,2, . . . , bM,k}. (10) To progress towards the goal, a target beam bT is defined that corresponds to the global goal direction projected into the son… view at source ↗
Figure 4
Figure 4. Figure 4: Spatial Context Generator Algorithm 1 EROAS Loop with SPD2C, SCG, and ST-CBF Require: sonar scan I, mission reference (G), current state, system parameters Ensure: safe reference commands (V S R , rR) 1: while goal not reached do 2: I ← Read FLS data() ▷ obtain the latest sonar scan 3: (VR, rR, mode, ΘP ) ← SPD2C(I,state, g) 4: if ΘP is defined then 5: Pivot the FLS(ΘP ) ▷ command a pivot scan if needed 6:… view at source ↗
Figure 5
Figure 5. Figure 5: Top view of AUV navigating through a 3D environment [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Yaw velocity with different algorithms [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
Figure 8
Figure 8. Figure 8: (a) Top view of AUV avoiding obstacle in 3D Gazebo environment and b) Side view of AUV avoiding obstacle in 3D [PITH_FULL_IMAGE:figures/full_fig_p009_8.png] view at source ↗
read the original abstract

Autonomous Underwater Vehicles (AUVs) have advanced significantly in obstacle detection and path planning through sonar, cameras, and learning-based methods. However, safe and efficient navigation in cluttered environments remains challenging due to partial observability, turbidity, the limited field-of-view of forward-looking sonar (FLS), and occlusions that obscure obstacle geometry. To address these issues, we propose the Efficient Reactive Obstacle Avoidance Strategy (EROAS), a lightweight framework that augments a standard 2D FLS with a pivoting mechanism, effectively transforming it into a cost-efficient \emph{2.5D sonar}. This design provides vertical information on demand, extending situational awareness while minimizing computational overhead. EROAS integrates three complementary modules: first, Sonar Profile-guided Directional Decision Control (SPD2C) for rapid gap detection and generation of reference commands in both horizontal and vertical planes. Secondly, the Spatial Context Generator (SCG), which maintains a short-term obstacle memory of the past to mitigate partial observability, and finally, a Spatio-Temporal Control Barrier Function (ST-CBF) that enforces forward-invariance of safety constraints by filtering nominal references. Together, these components enable robust, reactive avoidance of obstacles in uncertain and cluttered 3D underwater settings. Simulation and hardware-in-the-loop (HIL) experiments validate the efficacy of the proposed EROAS algorithm, demonstrating improved trajectory efficiency, reduced travel time, and enhanced safety compared to conventional methods such as the Dynamic Window Approach (DWA) and Artificial Potential Fields (APF). https://github.com/AIRLabIISc/EROAS

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper proposes EROAS, a lightweight reactive obstacle avoidance framework for AUVs that augments a standard 2D forward-looking sonar (FLS) with a pivoting mechanism to create cost-efficient 2.5D sensing. It integrates three modules—Sonar Profile-guided Directional Decision Control (SPD2C) for gap detection in horizontal/vertical planes, Spatial Context Generator (SCG) for short-term obstacle memory to handle partial observability, and Spatio-Temporal Control Barrier Function (ST-CBF) to enforce safety constraints—claiming robust 3D avoidance in cluttered, uncertain underwater environments. Simulation and HIL experiments report improved trajectory efficiency, reduced travel time, and better safety versus DWA and APF baselines.

Significance. If the mechanical and observability assumptions hold, the work offers a practical, low-overhead extension of existing 2D sonar hardware to 3D awareness without full 3D sensors, which could meaningfully advance field-deployable AUV navigation in turbid or occluded settings. The combination of directional control, memory augmentation, and barrier-function filtering is a coherent modular assembly, and the open-source release supports reproducibility.

major comments (3)
  1. [abstract and §3 (SPD2C and pivoting description)] The central efficiency claim rests on the pivoting mechanism supplying vertical information 'on demand' at low mechanical and computational cost (abstract and module description), yet no quantitative metrics on actuation latency, scanning schedule overhead, or power draw under realistic AUV dynamics are provided; this directly affects whether the 2.5D transformation remains lightweight.
  2. [§3 (SCG) and §5 (experiments)] The SCG short-term memory is asserted to compensate for partial observability and occlusions (abstract), but the experiments contain no ablation isolating SCG's contribution in occluded regimes, nor metrics on memory horizon versus occlusion duration; without these, the claim that SCG 'sufficiently compensates' cannot be evaluated against the weakest assumption.
  3. [§3 (ST-CBF) and §4 (safety analysis)] ST-CBF is presented as enforcing forward-invariance of safety constraints by filtering nominal references, but the manuscript provides no explicit derivation or parameter sensitivity analysis showing how the spatio-temporal formulation reduces to the reported safety margins; the soundness of the safety guarantee therefore remains unverified from the given component descriptions.
minor comments (2)
  1. [§5 figures] Figure captions and axis labels in the experimental results could more explicitly state the sonar resolution and pivoting angle range used in each trial.
  2. [§5 tables] The comparison tables would benefit from reporting standard deviations across repeated trials rather than single-run values to strengthen the statistical claim of improvement over DWA and APF.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive feedback on EROAS. The comments highlight areas where additional evidence would strengthen the efficiency, observability, and safety claims. We address each major comment below and indicate planned revisions.

read point-by-point responses

  1. Referee: [abstract and §3 (SPD2C and pivoting description)] The central efficiency claim rests on the pivoting mechanism supplying vertical information 'on demand' at low mechanical and computational cost (abstract and module description), yet no quantitative metrics on actuation latency, scanning schedule overhead, or power draw under realistic AUV dynamics are provided; this directly affects whether the 2.5D transformation remains lightweight.

    Authors: We agree that quantitative metrics on actuation latency, scanning schedule overhead, and power draw are absent from the current manuscript and would directly support the lightweight claim. The presented results focus on end-to-end navigation performance rather than component-level overhead. In the revised version we will add these measurements obtained from the HIL platform under representative AUV dynamics. revision: yes

  2. Referee: [§3 (SCG) and §5 (experiments)] The SCG short-term memory is asserted to compensate for partial observability and occlusions (abstract), but the experiments contain no ablation isolating SCG's contribution in occluded regimes, nor metrics on memory horizon versus occlusion duration; without these, the claim that SCG 'sufficiently compensates' cannot be evaluated against the weakest assumption.

    Authors: We concur that an ablation isolating SCG and explicit metrics relating memory horizon to occlusion duration are missing. The existing experiments report aggregate system behavior. We will incorporate an ablation study in the revised experiments section that compares trajectories with and without SCG across controlled occlusion durations and reports the corresponding memory-horizon statistics. revision: yes

  3. Referee: [§3 (ST-CBF) and §4 (safety analysis)] ST-CBF is presented as enforcing forward-invariance of safety constraints by filtering nominal references, but the manuscript provides no explicit derivation or parameter sensitivity analysis showing how the spatio-temporal formulation reduces to the reported safety margins; the soundness of the safety guarantee therefore remains unverified from the given component descriptions.

    Authors: We acknowledge that the current §4 does not contain a self-contained derivation or sensitivity analysis of the spatio-temporal CBF. The safety argument is summarized at a high level. In the revision we will expand the safety analysis with the full mathematical derivation of the ST-CBF forward-invariance property and include a parameter-sensitivity study that maps the reported safety margins to the formulation parameters. revision: yes

Circularity Check

0 steps flagged

No significant circularity; framework is modular assembly without self-referential reductions

full rationale

The paper describes EROAS as an integration of three modules (SPD2C for gap detection, SCG for short-term memory, ST-CBF for safety filtering) on a pivoting 2D FLS to enable 2.5D sensing. No equations, fitted parameters, or derivations appear in the provided text that reduce performance claims to inputs by construction. No self-citations are invoked as load-bearing uniqueness theorems, and the validation rests on simulation/HIL experiments against DWA and APF baselines. The central claim is an engineering assembly whose efficacy is asserted to be externally testable rather than tautological.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Review limited to abstract; no explicit free parameters, axioms, or invented entities are stated in the provided text.

pith-pipeline@v0.9.0 · 5857 in / 1141 out tokens · 23301 ms · 2026-05-23T17:36:47.175467+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

37 extracted references · 37 canonical work pages

  1. [1]

    Autosub long range 6000: A multiple-month endurance auv for deep-ocean monitoring and survey,

    D. Roper, C. A. Harris, G. Salavasidis, M. Pebody, R. Templeton, T. Prampart, M. Kingsland, R. Morrison, M. Furlong, A. B. Phillips, and S. McPhail, “Autosub long range 6000: A multiple-month endurance auv for deep-ocean monitoring and survey,”IEEE Journal of Oceanic Engineering, vol. 46, no. 4, pp. 1179–1191, 2021

    work page 2021

  2. [2]

    Autonomous Underwater Vehicle Navigation: A Review,

    B. Zhang, D. Ji, S. Liu, X. Zhu, and W. Xu, “Autonomous Underwater Vehicle Navigation: A Review,”Ocean Engineering, p. 113861, 2023

    work page 2023

  3. [3]

    Navigation in the presence of obstacles for an agile autonomous underwater vehicle,

    M. Xanthidis, N. Karapetyan, H. Damron, S. Rahman, J. Johnson, A. O’Connell, J. M. O’Kane, and I. Rekleitis, “Navigation in the presence of obstacles for an agile autonomous underwater vehicle,” in2020 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2020, pp. 892–899

    work page 2020

  4. [4]

    Robust trajectory tracking control for underactuated autonomous underwater vehicles in uncertain environments,

    S. Heshmati-Alamdari, A. Nikou, and D. V . Dimarogonas, “Robust trajectory tracking control for underactuated autonomous underwater vehicles in uncertain environments,”IEEE Transactions on Automation Science and Engineering, vol. 18, no. 3, pp. 1288–1301, 2021

    work page 2021

  5. [5]

    Evaluating the benefit of using multiple low-cost forward-looking sonar beams for collision avoidance in small auvs,

    C. Morency and D. J. Stilwell, “Evaluating the benefit of using multiple low-cost forward-looking sonar beams for collision avoidance in small auvs,” in2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022, pp. 8423–8429

    work page 2022

  6. [6]

    Transformer-based dual-channel self-attention for uuv autonomous collision avoidance,

    C. Lin, Y . Cheng, X. Wang, J. Yuan, and G. Wang, “Transformer-based dual-channel self-attention for uuv autonomous collision avoidance,” IEEE Transactions on Intelligent Vehicles, vol. 8, no. 3, pp. 2319–2331, 2023

    work page 2023

  7. [7]

    Collision avoidance with stochastic model predictive control for systems with a twofold uncertainty structure,

    T. Br ¨udigam, J. Zhan, D. Wollherr, and M. Leibold, “Collision avoidance with stochastic model predictive control for systems with a twofold uncertainty structure,” 2021. [Online]. Available: https://arxiv.org/abs/2106.08463

    work page arXiv 2021

  8. [8]

    Nonlinear lyapounov based control of an underwater vehicle in presence of uncertainties and obstacles,

    A. K. Khalaji and H. Tourajizadeh, “Nonlinear lyapounov based control of an underwater vehicle in presence of uncertainties and obstacles,” Ocean Engineering, vol. 198, p. 106998, 2020

    work page 2020

  9. [9]

    Planning feasible and safe paths online for autonomous underwater vehicles in unknown environments,

    J. D. Hern ´andez, M. Moll, E. Vidal, M. Carreras, and L. E. Kavraki, “Planning feasible and safe paths online for autonomous underwater vehicles in unknown environments,” in2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016, pp. 1313– 1320

    work page 2016

  10. [10]

    An auv collision avoidance algorithm in unknown environment with multiple constraints,

    N. Dai, P. Qin, X. Xu, Y . Zhang, Y . Shen, and B. He, “An auv collision avoidance algorithm in unknown environment with multiple constraints,” Ocean Engineering, vol. 294, p. 116846, 2024

    work page 2024

  11. [11]

    Uivnav: Underwater information-driven vision- based navigation via imitation learning,

    X. Lin, N. Karapetyan, K. Joshi, T. Liu, N. Chopra, M. Yu, P. Tokekar, and Y . Aloimonos, “Uivnav: Underwater information-driven vision- based navigation via imitation learning,” in2024 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2024, pp. 5250–5256

    work page 2024

  12. [12]

    Vision-based autonomous underwater vehicle navigation in poor visibility conditions using a model-free robust con- trol,

    R. P ´erez-Alcocer, L. A. Torres-M ´endez, E. Olgu ´ın-D´ıaz, and A. A. Maldonado-Ram´ırez, “Vision-based autonomous underwater vehicle navigation in poor visibility conditions using a model-free robust con- trol,”Journal of Sensors, vol. 2016, no. 1, p. 8594096, 2016

    work page 2016

  13. [13]

    Sensor fusion of two sonar devices for underwater 3d mapping with an auv,

    H. Joe, H. Cho, M. Sung, J. Kim, and S.-c. Yu, “Sensor fusion of two sonar devices for underwater 3d mapping with an auv,”Autonomous Robots, vol. 45, no. 4, pp. 543–560, 2021

    work page 2021

  14. [14]

    Intelligent vector field histogram based collision avoidance method for auv,

    G. Zhang, Y . Zhang, J. Xu, T. Chen, W. Zhang, and W. Xing, “Intelligent vector field histogram based collision avoidance method for auv,”Ocean Engineering, vol. 264, p. 112525, 2022

    work page 2022

  15. [15]

    A novel method for underactuated uuv tracking unknown contour based on forward-looking sonar,

    Z. Yan, X. Min, D. Xu, and D. Geng, “A novel method for underactuated uuv tracking unknown contour based on forward-looking sonar,”Ocean Engineering, vol. 301, p. 117545, 2024

    work page 2024

  16. [16]

    An end-to-end neural network for uuv autonomous collision avoidance,

    C. Lin, H. Wang, B. Li, H. Zhang, and J. Yuan, “An end-to-end neural network for uuv autonomous collision avoidance,”Ocean Engineering, vol. 289, p. 115995, 2023

    work page 2023

  17. [17]

    Real-time under- water localization in three-dimensional environment,

    T. Noda, H. Kondo, K. Nagaokaya, and T. Someya, “Real-time under- water localization in three-dimensional environment,”IEEE Journal of Oceanic Engineering, vol. 50, no. 3, pp. 1585–1595, 2025

    work page 2025

  18. [18]

    Target positioning of dual forward looking sonars based on orthogonal detection,

    W. Liu, Y . Li, L. Li, W. Zhang, and W. Huang, “Target positioning of dual forward looking sonars based on orthogonal detection,”Mechatron- ics, vol. 98, p. 103135, 2024

    work page 2024

  19. [19]

    High-precision underwater 3d mapping using imaging sonar for navigation of autonomous underwater vehicle,

    B. Kim, H. Joe, and S.-C. Yu, “High-precision underwater 3d mapping using imaging sonar for navigation of autonomous underwater vehicle,” International Journal of Control, Automation and Systems, vol. 19, no. 9, pp. 3199–3208, 2021

    work page 2021

  20. [20]

    Methodology for processing of 3d multibeam sonar big data for comparative navigation,

    A. Stateczny, W. Blaszczak-Bak, A. Sobieraj-Zlobinska, W. Motyl, and M. Wisniewska, “Methodology for processing of 3d multibeam sonar big data for comparative navigation,”Remote Sensing, vol. 11, no. 19, p. 2245, 2019

    work page 2019

  21. [21]

    Three-dimensional obstacle avoidance for autonomous underwater robot,

    W. Cai, Y . Wu, and M. Zhang, “Three-dimensional obstacle avoidance for autonomous underwater robot,”IEEE Sensors Letters, vol. 4, no. 11, pp. 1–4, 2020

    work page 2020

  22. [22]

    A 3d reactive collision avoidance algorithm for underactuated underwater vehicles,

    M. S. Wiig, K. Y . Pettersen, and T. R. Krogstad, “A 3d reactive collision avoidance algorithm for underactuated underwater vehicles,”Journal of Field Robotics, vol. 37, no. 6, pp. 1094–1122, 2020

    work page 2020

  23. [23]

    Deep reinforcement learning controller for 3d path following and collision avoidance by autonomous underwater vehicles,

    S. T. Havenstrøm, A. Rasheed, and O. San, “Deep reinforcement learning controller for 3d path following and collision avoidance by autonomous underwater vehicles,”Frontiers in Robotics and AI, vol. 7, p. 566037, 2021

    work page 2021

  24. [24]

    Bar-Shalom, X

    Y . Bar-Shalom, X. R. Li, and T. Kirubarajan,Estimation with applica- tions to tracking and navigation: theory algorithms and software. John Wiley & Sons, 2004

    work page 2004

  25. [25]

    Control barrier functions: Theory and applications,

    A. D. Ames, S. Coogan, M. Egerstedt, G. Notomista, K. Sreenath, and P. Tabuada, “Control barrier functions: Theory and applications,” in2019 18th European control conference (ECC). IEEE, 2019, pp. 3420–3431

    work page 2019

  26. [26]

    Collision avoidance with control barrier function for target tracking of an unmanned underwater vehicle

    Z. Deng, M. T. Zaman, and Z. Chu, “Collision avoidance with control barrier function for target tracking of an unmanned underwater vehicle.” Underwater Technology, vol. 37, no. 1, 2020

    work page 2020

  27. [27]

    Combining control barrier functions and behavior trees for multi-agent underwater coverage missions,

    ¨O. ¨Ozkahraman and P. ¨Ogren, “Combining control barrier functions and behavior trees for multi-agent underwater coverage missions,” in2020 59th IEEE Conference on Decision and Control (CDC). IEEE, 2020, pp. 5275–5282

    work page 2020

  28. [28]

    Safety-critical control for autonomous underwater vehicles with unknown disturbance using function approximator,

    C. Wang, B. Li, L. Song, X. Du, and X. Guan, “Safety-critical control for autonomous underwater vehicles with unknown disturbance using function approximator,”Ocean Engineering, vol. 287, p. 115828, 2023

    work page 2023

  29. [29]

    Safe and predictive path-planning of autonomous underwater vehicles in a dynamic cluttered environment,

    R. Makam, A. Nair, R. Majumder, and S. Sundaram, “Safe and predictive path-planning of autonomous underwater vehicles in a dynamic cluttered environment,” inOCEANS 2025 Brest, 2025, pp. 1–6

    work page 2025

  30. [30]

    A hybrid rrt*-cbf approach for safe navigation of autonomous underwater vehicles,

    R. Majumder, B. K. S., Y . R. S., and S. Sundaram, “A hybrid rrt*-cbf approach for safe navigation of autonomous underwater vehicles,” in OCEANS 2025 Brest, 2025, pp. 1–8

    work page 2025

  31. [31]

    Dave aquatic virtual environment: Toward a general underwater robotics simulator,

    M. M. Zhang, W.-S. Choi, J. Herman, D. Davis, C. V ogt, M. McCarrin, Y . Vijay, D. Dutia, W. Lew, S. Peterset al., “Dave aquatic virtual environment: Toward a general underwater robotics simulator,” in2022 IEEE/OES Autonomous Underwater Vehicles Symposium (AUV). IEEE, 2022, pp. 1–8

    work page 2022

  32. [32]

    Development and commissioning of a dp system for rov sf 30k,

    V . Berg, “Development and commissioning of a dp system for rov sf 30k,” Master’s thesis, Institutt for marin teknikk, 2012

    work page 2012

  33. [33]

    Physics-based modelling and simulation of multibeam echosounder perception for autonomous under- water manipulation,

    W.-S. Choi, D. R. Olson, D. Davis, M. Zhang, A. Racson, B. Bingham, M. McCarrin, C. V ogt, and J. Herman, “Physics-based modelling and simulation of multibeam echosounder perception for autonomous under- water manipulation,”Frontiers in Robotics and AI, vol. 8, p. 706646, 2021

    work page 2021

  34. [34]

    Auv slam method based on so-cfar and adt feature extraction,

    X. Mu, H. Chen, J. Wang, H. Qin, and Z. Zhu, “Auv slam method based on so-cfar and adt feature extraction,”Science Progress, vol. 107, no. 4, p. 00368504241286969, 2024

    work page 2024

  35. [35]

    Automatic collision avoidance al- gorithm based on route-plan-guided artificial potential field method,

    H. L. Zhongxian Zhu, Yong Yin, “Automatic collision avoidance al- gorithm based on route-plan-guided artificial potential field method,” Ocean Engineering, p. 113737, 2023

    work page 2023

  36. [36]

    Dynamic target hunting under autonomous underwater vehicle (auv) motion planning based on im- proved dynamic window approach (dwa),

    H. Z. Z. Z. Juan Li, Houtong Lu, “Dynamic target hunting under autonomous underwater vehicle (auv) motion planning based on im- proved dynamic window approach (dwa),”Journal of Marine Science and Engineering (JMSE), p. 13020221, 2025

    work page 2025

  37. [37]

    Local path planning of under-actuated auv based on vadwa considering dynamic model,

    Y . X. Z. D. H. Q. Jiahao Zhang, Zhongben Zhu, “Local path planning of under-actuated auv based on vadwa considering dynamic model,” Oceans, p. 118705, 2024

    work page 2024