The reviewed record of science sign in
Pith

arxiv: 2606.17630 · v1 · pith:M2JC4ECT · submitted 2026-06-16 · cs.RO

FLAP: FOV-Constrained Active Perception Planning for Prior-Map-Free 3D Navigation

Mengke Zhang , Sitong Li , Tiancheng Lai , Ruitian Pang , Mingxuan Zhang , Qingcheng Chen , Fei Gao , Chao Xu
show 1 more author
Yanjun Cao
This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel 2026-06-27 00:42 UTCgrok-4.3pith:M2JC4ECTrecord.jsonopen to challenge →

classification cs.RO
keywords active perceptiontrajectory optimizationUAV navigationfield of view constraints3D path planningunknown environmentsdifferentiable optimization
0
0 comments X

The pith

A trajectory optimization method adds field-of-view constraints to enable safe 3D UAV navigation without prior maps.

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

This paper presents a planning framework that directly integrates active perception into the trajectory optimization process for UAVs operating in unknown cluttered 3D spaces. Perception constraints are derived from the dynamic model and expressed in the sensor frame to accurately manage the limited viewing angle and range. A velocity-triggered activation and an optimizable perception sub-trajectory segment allow balancing of sensing and motion without conservative speed limits or fixed patterns. The entire setup is cast as a differentiable problem that accepts only a simple global path as input. This enables effective operation in arbitrary 3D maneuvers across different sensors.

Core claim

By deriving perception constraints from the UAV dynamic model in the sensor coordinate frame and introducing an active perception sub-trajectory with parametric start-time optimization, the method incorporates all constraints into a differentiable optimization that supports active perception during arbitrary 3D maneuvers using only a simple front-end global path.

What carries the argument

Active perception sub-trajectory segment with parametric start-time optimization, which balances perception and motion efficiency while mitigating collision risks from late obstacle detection.

Load-bearing premise

Perception constraints derived from the UAV's dynamic model in the sensor coordinate frame handle FOV geometry precisely without unmodeled sensing delays or dynamic mismatches invalidating collision avoidance.

What would settle it

An experiment showing a collision due to an obstacle entering the FOV later than predicted by the dynamic model, despite the planner satisfying all constraints.

Figures

Figures reproduced from arXiv: 2606.17630 by Chao Xu, Fei Gao, Mengke Zhang, Mingxuan Zhang, Qingcheng Chen, Ruitian Pang, Sitong Li, Tiancheng Lai, Yanjun Cao.

Figure 1
Figure 1. Figure 1: Simulation results of the proposed method in a dense grid of metal pipes without prior mapping. The UAV starts from the ground, actively perceives unknown spaces using its onboard vision sensor, successfully avoids all obstacles and reaches the final position above the pipes. and search-and-rescue missions. Our planner enables complex vertical maneuvers without pre-existing maps, which is valuable in confi… view at source ↗
Figure 2
Figure 2. Figure 2: Independent visualization of the three planning spaces: (a) safe-or￾unknown space Du, (b) known-safe space Ds, (c) conditionally-traversable space Da. We partition the trajectory into two parts: Ss in Ds and St in Da or Ds, separated by the known-unknown boundary plane B. The boundary point between safe segment Ss and transition segment St is initialized as pu0 and is optimized on B. safe space Ds and safe… view at source ↗
Figure 3
Figure 3. Figure 3: (a). We therefore define the visibility point pv by shifting pu along −nu, so that the safety of pu can be evaluated while keeping the UAV safely: pv = pu − d max Bs nu, (10) where d max Bs > ds is a distance parameter that encourages the UAV to observe further into the unknown region beyond the boundary B. We consider a generic onboard sensor with a finite sensing range and a bounded FOV. Its valid sensin… view at source ↗
Figure 4
Figure 4. Figure 4: Two representative sensor configurations. (a) Asymmetric vertical angular coverage of the Livox Mid-360 LiDAR. (b) Symmetric vertical angular coverage of a typical depth camera. • 3D LiDAR: A Livox Mid-360 LiDAR2 features a hori￾zontal FOV of 360◦ and a non-symmetric vertical FOV spanning approximately 52◦ upward and 7 ◦ downward, with a typical sensing range of 0.1 to 40 m. In our formulation, this is mod… view at source ↗
Figure 6
Figure 6. Figure 6: Comparison of the proposed AP segment with other strategies. (a) Ignoring the safety distance and evaluating the safety and perception constraints over the terminal part of Ss. (b) Considering the safety distance and evaluating the safety and perception constraints over the terminal part of Ss. (c) The proposed AP segment, which can be interpreted as containing safety-dominated, coupling, and perception-do… view at source ↗
Figure 8
Figure 8. Figure 8: Results of FLAP and SUPER in the overhead-obstacle scenario. The final point is set directly above the start point, and the UAV must actively observe the obstacle above to ensure safety. by imposing stricter acceleration and velocity limits through maximum tilt angle constraints, though at the cost of increased mission time. FLAP ensures safety through active perception, as illustrated in [PITH_FULL_IMAGE… view at source ↗
Figure 7
Figure 7. Figure 7: Results of FLAP, SUPER, and FM in the horizontal narrow-space scenario. We use gradient colors to represent the UAV’s speed; the darker the color, the higher the speed. From top to bottom are the results with total vertical FOVs of 90◦, 30◦, 10◦, and 0.2◦. The small fan-shaped inset at the right of each row illustrates the corresponding vertical sensing range. The successful trajectory is shown only if the… view at source ↗
Figure 9
Figure 9. Figure 9: Results of FLAP and SUPER in the U-shaped maze scenario. (a) Trajectories of the two methods, where color gradients encode the UAV altitude; the right side shows representative close-up views at two locations. (b) Two types of U-shaped obstacles in the environment, where two colors distinguish obstacles attached to the floor and the ceiling, and the orange lines mark their intersections with the ground or … view at source ↗
Figure 10
Figure 10. Figure 10: Comparison of FLAP, RAPTOR, FM, and NBV in the horizontal narrow-space scenario. unknown space, such methods typically select a frontier￾associated observation viewpoint and use it as a temporary goal, so that new regions can be observed. To mitigate the influence of trajectory parameterization on trajectory quality and computational cost, we also implement Next-Best-View (NBV) within the MINCO framework … view at source ↗
Figure 11
Figure 11. Figure 11: Once observation reveals that overflying the obstacle is infeasible, the UAV selects a lateral bypass, as shown at ④ and ⑤ in [PITH_FULL_IMAGE:figures/full_fig_p014_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Results of NBV (a), FM (b), and RAPTOR (c) in the overhead￾obstacle scenario. NBV reaches the goal conservatively, FM gets stuck below the obstacle, and RAPTOR collides during aggressive ascent [PITH_FULL_IMAGE:figures/full_fig_p015_12.png] view at source ↗
Figure 14
Figure 14. Figure 14: Performance of FLAP and NBV in a cluttered environment with overlapping vertical obstacles. The UAV, equipped with a vision camera, must traverse a vertically constrained passage formed by these obstacles. The trajectory is color-coded by height. The left and right figures show the results of FLAP and NBV, respectively. For visualization clarity, the pipeline walls are omitted in the figure to reveal the … view at source ↗
Figure 13
Figure 13. Figure 13: Performance of FLAP in the U-shaped maze scenario using a depth camera. The trajectory is color-coded by height, with the UAV’s orientation marked along the trajectory. At ①, ③, and ④, the UAV descends to navigate around tall obstacles detected on both sides. At ②, it ascends to bypass a lower obstacle. Notably, because the UAV has previously observed and stored obstacle information at current heights dur… view at source ↗
Figure 15
Figure 15. Figure 15: UAV platforms with three sensor configurations: (a) horizontal LiDAR, (b) inclined LiDAR, and (c) camera. The z-axes of the body frame B and the sensor frame S are shown. The LiDAR-equipped UAVs are fitted with passive wheels as a protective mechanism during safety tests [PITH_FULL_IMAGE:figures/full_fig_p015_15.png] view at source ↗
Figure 16
Figure 16. Figure 16: Experimental results with three UAV sensing configurations: (a) horizontal LiDAR, (b) inclined LiDAR, and (c) camera. The UAV must rely on onboard sensing to traverse a tall frontal obstacle and land on the far side. For the vision case, the UAV’s yaw angle along the trajectory is encoded by gradient colors. • Horizontal LiDAR: A Mid-360 LiDAR is mounted on the UAV with its z-axis parallel to the UAV’s z-… view at source ↗
Figure 17
Figure 17. Figure 17: Planning results for the UAV equipped with a LiDAR sensor under height-restricted (a) and unrestricted (b) vertical motion, in an environment with a tall frontal obstacle and a lower obstacle on the right. restricted strategy, which is commonly used for UAVs with limited vertical FOV, the UAV is constrained to search for feasible paths mainly in the horizontal direction. This reduces the risk of colliding… view at source ↗
Figure 18
Figure 18. Figure 18: Planning results for the UAV equipped with a camera sensor with restricted (a) and unrestricted (b) vertical motion in an L-shaped obstacle environment. planner adjusts its yaw angle at ③ to inspect a possible shortcut occluded by the obstacle (dashed box). After confirming the detour is necessary, it accelerates and observes the unknown space at ④ before reaching the goal. As shown in [PITH_FULL_IMAGE:f… view at source ↗
read the original abstract

Safe and efficient trajectory planning in unknown, cluttered 3D environments constitutes a critical bottleneck for deploying Unmanned Aerial Vehicles (UAVs) in real-world applications. This challenge is further exacerbated by the limited field-of-view (FOV) and sensing range of onboard sensors. Many existing methods either make simplistic assumptions about unexplored space or rely on conservative heuristics such as speed limits or fixed perception patterns, reducing efficiency and generalizing poorly across different sensor types. In this work, we propose a novel planning framework that directly integrates active perception into trajectory optimization, thereby improving safety while preserving efficiency. The perception constraints are derived from the UAV's dynamic model and formulated in the sensor coordinate frame, which enables precise handling of FOV geometry. The velocity-triggered activation mechanism enables the planner to balance perception and motion efficiency. We introduce an active perception sub-trajectory segment with parametric start-time optimization, mitigating collision risks from late obstacle detection. Our formulation enables active perception during arbitrary 3D maneuvers, extending beyond prior methods designed mainly for horizontal motion. All constraints and penalties are incorporated into a differentiable optimization problem, so the planner requires only a simple front-end global path for guidance, rather than a computationally expensive perception-aware path generator. Extensive simulations and real-world experiments demonstrate robust performance across diverse unknown environments with varying sensor configurations.

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

1 major / 0 minor

Summary. The manuscript presents FLAP, a planning framework for FOV-constrained active perception in prior-map-free 3D UAV navigation. Perception constraints are derived from the UAV dynamic model and expressed in the sensor coordinate frame; a velocity-triggered activation mechanism and an active-perception sub-trajectory with parametric start-time optimization are introduced. All elements are cast as a single differentiable optimization problem that accepts only a simple front-end global path. The authors state that the formulation supports arbitrary 3D maneuvers and report robust performance across simulations and real-world experiments with varying sensor configurations.

Significance. If the quantitative claims hold, the work would address a recognized bottleneck in UAV deployment by enabling safe active perception during full 3D motion without conservative speed limits or fixed perception patterns. The differentiable, constraint-based formulation that avoids a separate perception-aware path generator is a clear technical strength. The velocity-triggered and start-time mechanisms offer a principled way to trade perception against motion efficiency.

major comments (1)
  1. [Abstract] Abstract: the central claim of 'robust performance' and 'extensive simulations and real-world experiments' is unsupported by any quantitative results, error metrics, ablation studies, or baseline comparisons. Without these data the effectiveness of the FOV constraints, velocity-triggered activation, and parametric start-time optimization cannot be assessed.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback. We address the single major comment below and agree that the abstract requires strengthening with quantitative support.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claim of 'robust performance' and 'extensive simulations and real-world experiments' is unsupported by any quantitative results, error metrics, ablation studies, or baseline comparisons. Without these data the effectiveness of the FOV constraints, velocity-triggered activation, and parametric start-time optimization cannot be assessed.

    Authors: We agree that the abstract, as currently written, does not include quantitative metrics and therefore does not itself substantiate the performance claims. The body of the manuscript contains the requested quantitative evaluations (success rates, trajectory efficiency, computation times, ablation studies on the velocity-triggered and start-time mechanisms, and baseline comparisons) in the Experiments section. To directly resolve the referee's concern we will revise the abstract to incorporate specific numerical highlights drawn from those results, thereby making the claims self-contained and verifiable within the abstract itself. revision: yes

Circularity Check

0 steps flagged

No significant circularity identified

full rationale

The paper's abstract and described formulation derive perception constraints directly from the UAV dynamic model in the sensor frame, incorporate them into a differentiable optimization problem, and use a velocity-triggered activation with parametric start-time optimization. No equations, fitted parameters, self-citations, or ansatzes are presented that reduce any claimed prediction or result to its own inputs by construction. The central claim of enabling active perception in arbitrary 3D maneuvers via a simple front-end path rests on the stated differentiability and completeness of these constraints, which are presented as independent derivations rather than self-referential. This matches the reader's assessment of no visible circular reduction.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Abstract-only review; no explicit free parameters, axioms, or invented entities are stated. The method implicitly assumes accurate UAV dynamics and sensor models suffice for constraint derivation.

axioms (1)
  • domain assumption UAV dynamic model accurately predicts motion for deriving perception constraints in sensor frame
    Abstract states constraints are derived from the dynamic model without further qualification.

pith-pipeline@v0.9.1-grok · 5793 in / 1234 out tokens · 36457 ms · 2026-06-27T00:42:40.986946+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

39 extracted references · 3 canonical work pages · 1 internal anchor

  1. [1]

    Ego-planner: An esdf- free gradient-based local planner for quadrotors,

    X. Zhou, Z. Wang, H. Ye, C. Xu, and F. Gao, “Ego-planner: An esdf- free gradient-based local planner for quadrotors,”IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 478–485, 2020

    2020

  2. [2]

    Flying on point clouds: Online trajectory generation and autonomous navigation for quadrotors in cluttered environments,

    F. Gao, W. Wu, W. Gao, and S. Shen, “Flying on point clouds: Online trajectory generation and autonomous navigation for quadrotors in cluttered environments,”Journal of Field Robotics, vol. 36, no. 4, pp. 710–733, 2019

    2019

  3. [3]

    Autonomous navigation in unknown environments using sparse kernel-based occupancy mapping,

    T. Duong, N. Das, M. Yip, and N. Atanasov, “Autonomous navigation in unknown environments using sparse kernel-based occupancy mapping,” in2020 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2020, pp. 9666–9672

    2020

  4. [4]

    Universal trajectory optimization framework for differential drive robot class,

    M. Zhang, N. Chen, H. Wang, J. Qiu, Z. Han, Q. Ren, C. Xu, F. Gao, and Y . Cao, “Universal trajectory optimization framework for differential drive robot class,”IEEE Transactions on Automation Science and Engineering, 2025. 18

    2025

  5. [5]

    The determination of next best views,

    C. Connolly, “The determination of next best views,” inProceedings. 1985 IEEE international conference on robotics and automation, vol. 2. IEEE, 1985, pp. 432–435

    1985

  6. [6]

    Safe local explo- ration for replanning in cluttered unknown environments for microaerial vehicles,

    H. Oleynikova, Z. Taylor, R. Siegwart, and J. Nieto, “Safe local explo- ration for replanning in cluttered unknown environments for microaerial vehicles,”IEEE Robotics and Automation Letters, vol. 3, no. 3, pp. 1474–1481, 2018

    2018

  7. [7]

    Safe receding horizon path planning for autonomous vehicles,

    T. Schouwenaars, ´E. F ´eron, and J. How, “Safe receding horizon path planning for autonomous vehicles,” inProceedings of the Annual Aller- ton Conference on Communication Control and Computing, vol. 40, no. 1. The University; 1998, 2002, pp. 295–304

    1998

  8. [8]

    An efficient reachability-based framework for provably safe autonomous navigation in unknown environments,

    A. Bajcsy, S. Bansal, E. Bronstein, V . Tolani, and C. J. Tomlin, “An efficient reachability-based framework for provably safe autonomous navigation in unknown environments,” in2019 IEEE 58th Conference on Decision and Control (CDC). IEEE, 2019, pp. 1758–1765

    2019

  9. [9]

    Dwa-3d: A reactive planner for robust and efficient autonomous uav navigation,

    J. Bes, J. Dendarieta, L. Riazuelo, and L. Montano, “Dwa-3d: A reactive planner for robust and efficient autonomous uav navigation,”arXiv preprint arXiv:2409.05421, 2024

    work page arXiv 2024

  10. [10]

    High speed navigation for quadrotors with limited onboard sensing,

    S. Liu, M. Watterson, S. Tang, and V . Kumar, “High speed navigation for quadrotors with limited onboard sensing,” in2016 IEEE international conference on robotics and automation (ICRA). IEEE, 2016, pp. 1484– 1491

    2016

  11. [11]

    Toward autonomy of micro aerial vehicles in unknown and global positioning system denied environments,

    Y . Zhou, S. Lai, H. Cheng, A. H. M. Redhwan, P. Wang, J. Zhu, Z. Gao, Z. Ma, Y . Bi, F. Linet al., “Toward autonomy of micro aerial vehicles in unknown and global positioning system denied environments,”IEEE Transactions on Industrial Electronics, vol. 68, no. 8, pp. 7642–7651, 2020

    2020

  12. [12]

    Aggressive 3-d collision avoidance for high-speed navigation

    B. T. Lopez and J. P. How, “Aggressive 3-d collision avoidance for high-speed navigation.” inICRA, 2017, pp. 5759–5765

    2017

  13. [13]

    Collision avoidance with limited field of view sensing: A velocity obstacle approach,

    S. Roelofsen, D. Gillet, and A. Martinoli, “Collision avoidance with limited field of view sensing: A velocity obstacle approach,” in2017 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2017, pp. 1922–1927

    2017

  14. [14]

    History-aware autonomous exploration in confined environments using mavs,

    C. Witting, M. Fehr, R. B ¨ahnemann, H. Oleynikova, and R. Siegwart, “History-aware autonomous exploration in confined environments using mavs,” in2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2018, pp. 1–9

    2018

  15. [15]

    Autonomous robotic exploration by incremental road map construction,

    C. Wang, W. Chi, Y . Sun, and M. Q.-H. Meng, “Autonomous robotic exploration by incremental road map construction,”IEEE Transactions on Automation Science and Engineering, vol. 16, no. 4, pp. 1720–1731, 2019

    2019

  16. [16]

    Fuel: Fast uav exploration using incremental frontier structure and hierarchical planning,

    B. Zhou, Y . Zhang, X. Chen, and S. Shen, “Fuel: Fast uav exploration using incremental frontier structure and hierarchical planning,”IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 779–786, 2021

    2021

  17. [17]

    Eva-planner: Environmental adaptive quadrotor planning,

    L. Quan, Z. Zhang, X. Zhong, C. Xu, and F. Gao, “Eva-planner: Environmental adaptive quadrotor planning,” in2021 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2021, pp. 398– 404

    2021

  18. [18]

    Speed adaptive robot trajectory generation based on derivative property of b-spline curve,

    L. Wang and Y . Guo, “Speed adaptive robot trajectory generation based on derivative property of b-spline curve,”IEEE Robotics and Automation Letters, vol. 8, no. 4, pp. 1905–1911, 2023

    1905

  19. [19]

    Learning agility adaptation for flight in clutter,

    G. Zhao, T. Wu, Y . Chen, and F. Gao, “Learning agility adaptation for flight in clutter,”arXiv preprint arXiv:2403.04586, 2024

    work page arXiv 2024

  20. [20]

    Flight with limited field of view: A parallel and gradient-free strategy for micro aerial vehicle,

    H. Lu, Q. Zong, S. Lai, B. Tian, and L. Xie, “Flight with limited field of view: A parallel and gradient-free strategy for micro aerial vehicle,” IEEE Transactions on Industrial Electronics, vol. 69, no. 9, pp. 9258– 9267, 2021

    2021

  21. [21]

    Real-time perception-limited motion planning using sampling- based mpc,

    ——, “Real-time perception-limited motion planning using sampling- based mpc,”IEEE Transactions on Industrial Electronics, vol. 69, no. 12, pp. 13 182–13 191, 2022

    2022

  22. [22]

    Bayesian learning for safe high-speed navigation in unknown environments,

    C. Richter, W. Vega-Brown, and N. Roy, “Bayesian learning for safe high-speed navigation in unknown environments,” inRobotics Research: V olume 2. Springer, 2017, pp. 325–341

    2017

  23. [23]

    Planning high-speed safe trajectories in confidence-rich maps,

    E. Heiden, K. Hausman, G. S. Sukhatme, and A.-a. Agha-mohammadi, “Planning high-speed safe trajectories in confidence-rich maps,” in2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2017, pp. 2880–2886

    2017

  24. [24]

    Planning in dynamic and partially unknown environments,

    K. Miller, C. Fan, and S. Mitra, “Planning in dynamic and partially unknown environments,”IF AC-PapersOnLine, vol. 54, no. 5, pp. 169– 174, 2021

    2021

  25. [25]

    High- speed robot navigation using predicted occupancy maps,

    K. D. Katyal, A. Polevoy, J. Moore, C. Knuth, and K. M. Popek, “High- speed robot navigation using predicted occupancy maps,” in2021 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2021, pp. 5476–5482

    2021

  26. [26]

    Online mapping and motion planning under uncertainty for safe nav- igation in unknown environments,

    `E. Pairet, J. D. Hern ´andez, M. Carreras, Y . Petillot, and M. Lahijanian, “Online mapping and motion planning under uncertainty for safe nav- igation in unknown environments,”IEEE Transactions on Automation Science and Engineering, vol. 19, no. 4, pp. 3356–3378, 2021

    2021

  27. [27]

    Faster: Fast and safe trajectory planner for navigation in unknown environments,

    J. Tordesillas, B. T. Lopez, M. Everett, and J. P. How, “Faster: Fast and safe trajectory planner for navigation in unknown environments,”IEEE Transactions on Robotics, vol. 38, no. 2, pp. 922–938, 2021

    2021

  28. [28]

    Multitrajectory model pre- dictive control for safe uav navigation in an unknown environment,

    D. Saccani, L. Cecchin, and L. Fagiano, “Multitrajectory model pre- dictive control for safe uav navigation in an unknown environment,” IEEE Transactions on Control Systems Technology, vol. 31, no. 5, pp. 1982–1997, 2022

    1982

  29. [29]

    Safety-assured high-speed navigation for mavs,

    Y . Ren, F. Zhu, G. Lu, Y . Cai, L. Yin, F. Kong, J. Lin, N. Chen, and F. Zhang, “Safety-assured high-speed navigation for mavs,”Science Robotics, vol. 10, no. 98, p. eado6187, 2025

    2025

  30. [30]

    Estimating visibility from alternate perspectives for motion planning with occlusions,

    B. Gilhuly, A. Sadeghi, and S. L. Smith, “Estimating visibility from alternate perspectives for motion planning with occlusions,”IEEE Robotics and Automation Letters, 2024

    2024

  31. [31]

    Negotiating visibility for safe autonomous navigation in occluding and uncertain environments,

    J. Higgins and N. Bezzo, “Negotiating visibility for safe autonomous navigation in occluding and uncertain environments,”IEEE Robotics and Automation Letters, vol. 6, no. 3, pp. 4409–4416, 2021

    2021

  32. [32]

    Safe Motion Planning in Unknown Environments: Optimality Benchmarks and Tractable Policies

    L. Janson, T. Hu, and M. Pavone, “Safe motion planning in unknown environments: Optimality benchmarks and tractable policies,”arXiv preprint arXiv:1804.05804, 2018

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  33. [33]

    Search-based 3d planning and trajectory optimization for safe micro aerial vehicle flight under sensor visibility constraints,

    M. Nieuwenhuisen and S. Behnke, “Search-based 3d planning and trajectory optimization for safe micro aerial vehicle flight under sensor visibility constraints,” in2019 International Conference on Robotics and Automation (ICRA). IEEE, 2019, pp. 9123–9129

    2019

  34. [34]

    Cpa-planner: Motion planner with complete perception awareness for sensing-limited quadrotors,

    Q. Yu, C. Qin, L. Luo, H. H.-T. Liu, and S. Hu, “Cpa-planner: Motion planner with complete perception awareness for sensing-limited quadrotors,”IEEE Robotics and Automation Letters, vol. 8, no. 2, pp. 720–727, 2022

    2022

  35. [35]

    Learning to plan for visibility in navigation of unknown environments,

    C. Richter and N. Roy, “Learning to plan for visibility in navigation of unknown environments,” in2016 International Symposium on Experi- mental Robotics. Springer, 2017, pp. 387–398

    2017

  36. [36]

    Raptor: Robust and perception- aware trajectory replanning for quadrotor fast flight,

    B. Zhou, J. Pan, F. Gao, and S. Shen, “Raptor: Robust and perception- aware trajectory replanning for quadrotor fast flight,”IEEE Transactions on Robotics, vol. 37, no. 6, pp. 1992–2009, 2021

    1992

  37. [37]

    A model predictive-based motion planning method for safe and agile traversal of unknown and occluding environ- ments,

    J. Higgins and N. Bezzo, “A model predictive-based motion planning method for safe and agile traversal of unknown and occluding environ- ments,” in2022 International Conference on Robotics and Automation (ICRA). IEEE, 2022, pp. 9092–9098

    2022

  38. [38]

    Robust trajectory planning for spatial- temporal multi-drone coordination in large scenes,

    Z. Wang, C. Xu, and F. Gao, “Robust trajectory planning for spatial- temporal multi-drone coordination in large scenes,” in2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2022, pp. 12 182–12 188

    2022

  39. [39]

    Geometrically constrained tra- jectory optimization for multicopters,

    Z. Wang, X. Zhou, C. Xu, and F. Gao, “Geometrically constrained tra- jectory optimization for multicopters,”IEEE Transactions on Robotics, 2022

    2022