Efficient Knowledge Transfer for Jump-Starting Control Policy Learning of Multirotors through Physics-Aware Neural Architectures

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.

Training and transferring learning-based policies for quadrotors from simulation to reality remains challenging due to inefficient visual rendering, physical modeling inaccuracies, unmodeled sensor discrepancies, and the absence of a unified platform integrating differentiable physics learning into end-to-end training. While recent work has demonstrated various end-to-end quadrotor control tasks, few systems provide a systematic, zero-shot transfer pipeline, hindering reproducibility and real-world deployment. To bridge this gap, we introduce E2E-Fly, an integrated framework featuring an agile quadrotor platform coupled with a full-stack training, validation, and deployment workflow. The training framework incorporates a high-performance simulator with support for differentiable physics learning and reinforcement learning, alongside structured reward design tailored to common quadrotor tasks. We further introduce a two-stage validation strategy using sim-to-sim transfer and hardware-in-the-loop testing, and deploy policies onto two physical quadrotor platforms via a dedicated low-level control interface and a comprehensive sim-to-real alignment methodology, encompassing system identification, domain randomization, latency compensation, and noise modeling. To the best of our knowledge, this is the first work to systematically unify differentiable physical learning with training, validation, and real-world deployment for quadrotors. Finally, we demonstrate the effectiveness of our framework for training six end-to-end control tasks and deploy them in the real world.

The performance of learned robot visuomotor policies depends heavily on the size and quality of their training data, yet collecting high-quality demonstrations remains costly for robots in the real world. Although large-scale robot and human datasets are increasingly available, embodiment gaps and mismatched action spaces make them difficult to leverage directly. Cross-embodiment transfer, reusing experience from other embodiments to improve learning on a target embodiment, is therefore crucial for scaling robot learning beyond per-robot data collection. In this work, we find that efficient transfer can be achieved by learning from what is shared across embodiments, the visual dynamics of how the world responds to motion, and by effectively exploiting the scarce target-embodiment data at test time. The proposed framework, called Latent Policy Steering (LPS), implements an embodiment-agnostic pretraining phase, which trains an image-based World Model (WM) with optical flow across diverse embodiments. The resulting WM is finetuned on the target embodiment with robot actions. It then steers the base policy toward better actions by searching in the WM's latent space for plans that stay close to the finetuning data. LPS is a policy-agnostic framework: it can flexibly accommodate different policies without having to retrain them. In Robomimic and real-world evaluations, LPS improves the average performance of Diffusion Policy relatively by 16% and 62%, and Pi0.5 by 8% and 14%, with only 50 demonstrations on an unseen target embodiment.