Multimodal Sensor-Gated Mid-Air Launch and Vision-Based Recovery of a Child UAV on a Hovering Mothership Drone

Aashish Sahu; R. Prasanth Kumar

cs.ROOct 11, 2026

Multimodal Sensor-Gated Mid-Air Launch and Vision-Based Recovery of a Child UAV on a Hovering Mothership Drone

Authors: Aashish Sahu, R. Prasanth Kumar

Organizations: Department of Mechanical and Aerospace Engineering, Indian Institute of Technology Hyderabad, Kandi, Sangareddy 502284, India · Department of Artificial Intelligence, Indian Institute of Technology Hyderabad, Kandi, Sangareddy 502284, India

Abstract

Launching a micro unmanned aerial vehicle (UAV) from a hovering carrier and recovering it in flight requires reliable confirmation that the child is securely seated before the carrier is allowed to descend. This is challenging because vision provides relative guidance but does not directly indicate load transfer, and a downward-facing camera can lose its fiducial near touchdown. This letter presents a mothership-child quadrotor system in which mission transitions are gated by complementary nonvisual sensing. An upward-facing single-beam LiDAR on the recovery deck provides a binary occupancy state using hysteresis and a debounce interval derived from the child's occluding footprint and crossing speed; real-time kinematic (RTK) positioning conditions the carrier hover; and carrier thrust provides a proprioceptive indication of load transfer. In ten outdoor missions using an F450-class mothership and a Q250-class child with camera-guided recovery, nine completed successfully while RTK-fixed positioning was maintained through release and capture. A complementary MuJoCo study of fully autonomous fiducial-based recovery achieved touchdown 0.077 m from the deck center, while marker detection was lost within the final approximately 0.2 m above the docked configuration. In simulation, carrier thrust changed by -17.0 N at release and +17.3 N at capture, agreeing within 6% with the child's 18.0 N hover thrust. The results support a sensing architecture in which vision guides the approach, while range and proprioceptive information corroborate the final docking decision.

Figures & tables

Figure 1: Sensing architecture and supervisor. Release guard $g_{\mathrm{rel}}$ requires RTK-fixed positioning, bounded hover error, and $o_{k}\!:\!1\!\to\!0$ . Capture guard $g_{\mathrm{cap}}$ requires $o_{k}\!=\!1$ for $\tau_{d}$ ; thrust provides an independent load-transfer cue.

Panel of Figure 2 — Figure 2: Outdoor mission. (a) Child seated on the instrumented deck. (b) Joint hover at 5 m. (c) Mid-air release. (d) Outbound flight while the mothership holds position. (e) Camera-guided recovery with LiDAR occupancy confirmation. (f) Autonomous joint landing.

Figure 3: Mothership normalized thrust command and magnetic-field magnitude during a representative outdoor mission. A: takeoff; B: child release; C: recovery/landing disturbance; D: joint touchdown.

Figure 4: MuJoCo telemetry. (a) Mothership and child altitudes. (b) Planar error $e_{xy}$ and marker-detection state. (c) Mothership thrust $T_{M}$ and scaled child thrust $T_{C}$ . Background colors indicate mission phases.

Panel of Figure 5 — Figure 5: Child downward-camera view in MuJoCo; $h$ denotes height above the docked configuration. (a) Reacquisition after release. (b) Terminal-approach initialization. (c) Last detection near touchdown. (d) Marker overfills the field of view and detection is lost.

Outdoor flights (10 missions)
Metric	Value
End-to-end mission success	9/10
Deck occupancy sensor	TFmini Plus, $\tau_{d}=0.6$ s
GNSS at release and recovery	RTK fixed, 27 sat.
MuJoCo autonomous recovery (single run)
Release / dock / mission end	6.5 / 55.2 / 78.3 s

Table 1: Performance Summary

Event	LiDAR $o_{k}$	Marker	$\Delta\hat{m}$	Action
Child seated	1	–	–	Joint takeoff/hover
Release	$1\!\to\!0$	blind	$-m_{C}$	Hold position
Child away	0	lost/seen	0	Descent inhibited
Fast deck pass	stays 0	blind	0	Keep holding
Low hover	may rise	blind	$\approx 0$	Needs corroboration
Touchdown	$0\!\to\!1$	blind	$+m_{C}$	Settle, descend

Table 2: Sensor Evidence and Mothership Action per Event

Aerial Robotics

Aerial robotics studies the design, perception, control, and coordination of flying robots for navigation, inspection, transport, and physical interaction.

See all 329 papers

Integrated Guidance and Control of a Mother-Child UAV-UGV System for Cooperative Missions
Sep 17, 2026Aashish Sahu, R. Prasanth KumarAerial Robotics Multi-Robot Coordination
Department of Mechanical & Aerospace Engineering, Indian Institute of Technology Hyderabad, Telangana, India | Department of Artificial Intelligence, Indian Institute of Technology Hyderabad, Telangana, India
RTK-Vision PPO for Autonomous Micro UAV Recovery on an Airborne Carrier
Sep 17, 2026Aashish Sahu, R Prasanth KumarAerial Robotics Robot Policy Learning
Department of Mechanical and Aerospace Engineering Indian Institute of Technology Hyderabad Kandi, Sangareddy, India · Department of Artificial Intelligence Indian Institute of Technology Hyderabad Kandi, Sangareddy, India
Vision-Based Agile Landing on Turbulent Waters
May 22, 2026Dimosthenis Angelis, Leonard Bauersfeld, Davide Scaramuzza +1RL for Robotics Aerial Robotics
Department of Electrical and Photonics Engineering, Technical University of Denmark, Kgs. Lyngby, Denmark · Robotics and Perception Group, Department of Informatics, University of Zurich, Zurich, Switzerland

Sep 17, 2026J/K move · Enter open · S save

Integrated Guidance and Control of a Mother-Child UAV-UGV System for Cooperative Missions

Aashish Sahu, R. Prasanth Kumar

Department of Mechanical & Aerospace Engineering, Indian Institute of Technology Hyderabad, Telangana, India | Department of Artificial Intelligence, Indian Institute of Technology Hyderabad, Telangana, India

Aerial Robotics Multi-Robot Coordination Quadrotor Control

Open paper AskPDF arXiv

Autonomous recovery of a small multirotor onto a hovering multirotor carrier differs from recovery onto ground or shipborne platforms because the recovery surface is itself an actively controlled, thrust-limited aerial vehicle. This paper presents a field-validated autonomy framework for a heterogeneous rover-mothership-child system executing rover supervision, mothership transit, child deployment and sortie, autonomous return, aerial recovery, and synchronized descent. The recovery stack combines jerk-bounded reference generation, disturbance-observer-augmented planar tracking, feasibility-aware vertical control, a discrete-time barrier-based safety filter for relative vertical geometry, and communication-aware carrier-state prediction. The contribution is the coordinated system-level integration of these methods for recovery onto a hovering multirotor and its full-scale outdoor validation. The framework is implemented on a PX4-ROS 2 architecture using RTK-enabled GNSS, IMU, and barometric fusion, with mothership-side 1D lidar used only as an auxiliary near-contact cue. RTK-fixed positioning was maintained throughout testing. Across 20 outdoor cooperative missions, 17 successfully completed deployment, sortie, and recovery, giving an observed mission success rate of 85%. For successful recoveries, mean terminal-alignment time was 6.3 s, mean planar alignment error at acceptance was 0.18 m, maximum terminal planar deviation was 0.32 m within a 0.40 m capture radius, and minimum logged relative vertical separation during coupled descent was 0.41 m. Mothership planar station-keeping RMS error was 0.25 m. The three unsuccessful trials occurred at different mission stages and are analyzed separately. Results demonstrate practical autonomous aerial recovery within the tested outdoor operating envelope.

Abstract

Aerial Robotics

Explore similar work

Integrated Guidance and Control of a Mother-Child UAV-UGV System for Cooperative Missions

RTK-Vision PPO for Autonomous Micro UAV Recovery on an Airborne Carrier

Vision-Based Agile Landing on Turbulent Waters