SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2606.10857 · 2026

Embodiment-conditioned Generalist Control for Multirotor Aerial Robots

Orestis Konstantaropoulos, Welf Rehberg, Mihir Kulkarni, Kostas Alexis

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 8 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
ntnu-arl/generalist_multirotor_control canonical 8 of 8
FunctionStatusWhere it lives
compute_vee_map Ran ntnu-arl/generalist_multirotor_control/generalist_multirotor_control/utils/math_utils.py
pointer only (licence: NONE) · get_code("101b1a4066dd417b")
exp_penalty_func Ran ntnu-arl/generalist_multirotor_control/generalist_multirotor_control/simulator/multirotor_dynamics_env.py
pointer only (licence: NONE) · get_code("491d61084e5eaeab")
exp_rew_func Ran ntnu-arl/generalist_multirotor_control/generalist_multirotor_control/simulator/multirotor_dynamics_env.py
pointer only (licence: NONE) · get_code("d8d904b5694d4a6b")
quat_rotate Ran ntnu-arl/generalist_multirotor_control/generalist_multirotor_control/airframe_generation/sampler.py
pointer only (licence: NONE) · get_code("fd3708088644d5d4")
quat_rotate_multidim Ran ntnu-arl/generalist_multirotor_control/generalist_multirotor_control/airframe_generation/sampler.py
pointer only (licence: NONE) · get_code("8de1a77b319bd058")
sample_quaternion Ran ntnu-arl/generalist_multirotor_control/generalist_multirotor_control/airframe_generation/sampler.py
pointer only (licence: NONE) · get_code("3bc4d56deb62f173")
ssa Ran ntnu-arl/generalist_multirotor_control/generalist_multirotor_control/simulator/multirotor_dynamics_env.py
pointer only (licence: NONE) · get_code("9a08025bbdd6bc17")
update_config Ran ntnu-arl/generalist_multirotor_control/generalist_multirotor_control/rl_training/rl_games/runner.py
pointer only (licence: NONE) · get_code("da5221ab9fb4640d")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We present a generalist position control policy capable of controlling arbitrary multirotor configurations of a certain rotor count (e.g., hexarotors or quadrotors) with a single set of network weights. The policy is conditioned on a physics-grounded embodiment descriptor: a mass and inertia-normalized control allocation matrix that captures how mass-normalized motor thrusts generate linear and angular accelerations in the body-frame. To train the policy, we sample from a broad distribution of arbitrary multirotor configurations, including non-planar and asymmetric systems, and optimize a single, compact network using Proximal Policy Optimization. Training requires only five minutes on an RTX 3090 GPU using a custom NVIDIA Warp-based dynamics simulator. Through extensive simulation experiments, we show that embodiment conditioning enables robust generalist control across arbitrary morphologies. We demonstrate zero-shot real-world transfer of this generalist policy on three diverse hexarotor systems, including a planar robot, a partially symmetric non-planar system, and a random asymmetric, non-planar configuration.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2606.10857")
get_code_for_paper("2606.10857")
have("2606.10857")

Connect an agent — have() is free.