AcroRL: Learning Aggressive Quadrotor Inversion using Bidirectional Thrust

AIPR assessment

Single-domain robotics and control paper, with all evidence concentrated on a hard, specialized maneuver rather than a broad benchmark. The task is challenging but not massively crowded, and the paper's strengths reinforce each other: realistic hardware validation, open-source code, and a clean baseline comparison make the main result believable and usable. The weaknesses also interact: the narrow hardware setting, limited ablation depth, and small number of physical trials mean the result is st

Abstract

Bidirectional thrust grants quadrotors a second equilibrium condition and increased control authority, expanding the envelope of possible aggressive maneuvers and enabling inverted flight, perching, and sensing. Prior geometric control approaches extend differential flatness through Hopf fibration-based attitude representations to support bidirectional thrust, but struggle with actuator saturation and motor reversal delay during inversions, requiring heuristic thrust posture scheduling and waypoint tuning. We propose a learning-based framework that modulates a constant reference trajectory to perform compact, position-constrained quadrotor inversions while remaining compatible with traditional trajectory generation and tracking across flight regimes. Separate policies are trained via reinforcement learning for nominal-to-inverted and inverted-to-nominal transitions. In JAX-based simulation, the proposed method achieves the lowest position deviation and settling time across all evaluated baselines, reducing position root mean square error (RMSE) by 32% and settling time by 57% relative to the strongest optimization-based baseline. Hardware experiments demonstrate successful inversion across multiple yaw configurations with position RMSE below 0.35m, and compatibility with downstream trajectory generation and control through circular flight in both regimes. Additionally, we provide an open-source implementation of the proposed framework.

Score Breakdown

More from this week

• Optimus: Elastic Decoding for Efficient Diffusion LLM Serving
• TubiFM: Unified Item, Carousel, and Search Ranking for Streaming Discovery
• Context Features Are Cheap: Rank-Aware Decomposition for Efficient Feature Interaction in Recommender Systems
• Rethinking Continual Anomaly Detection on the Edge: Benchmarking Under Realistic Industrial Conditions
• Learning High-Frequency Continuous Action Chunks in Latent Space

More in Robotics

• Benchmarking Vision-Language-Action Models on SO-101: Failure and Recovery Analysis
• vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models
• Learning High-Frequency Continuous Action Chunks in Latent Space
• Dynamic Neural Koopman Distillation for Real-Time Robot Control Using Diffusion Models
• 123D: Unifying Multi-Modal Autonomous Driving Data at Scale