# ManeuverNet: A Soft Actor-Critic Framework for Precise Maneuvering of Double-Ackermann-Steering Robots with Optimized Reward Functions

arXiv: https://arxiv.org/abs/2602.14726 · HTML: https://mlsanity.com/paper/2602.14726/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 16 Feb 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 17 of 17)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey](https://mlsanity.com/paper/2009.13303/) (2020)
- [Goal-Conditioned Reinforcement Learning: Problems and Solutions](https://mlsanity.com/paper/2201.08299/) (2022)
- [CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity](https://mlsanity.com/paper/1902.05605/) (2019)
- [FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing](https://mlsanity.com/paper/2304.09831/) (2023)
- [Generalization in Deep Reinforcement Learning for Robotic Navigation by Reward Shaping](https://mlsanity.com/paper/2209.14271/) (2022)
- [FRASA: An End-to-End Reinforcement Learning Agent for Fall Recovery and Stand Up of Humanoid Robots](https://mlsanity.com/paper/2410.08655/) (2024)
- [Terrain-Attentive Learning for Efficient 6-DoF Kinodynamic Modeling on Vertically Challenging Terrain](https://mlsanity.com/paper/2403.16419/) (2024)
- [Deep Reinforcement Learning for Continuous Docking Control of Autonomous Underwater Vehicles: A Benchmarking Study](https://mlsanity.com/paper/2108.02665/) (2021)
- [Multi Actor-Critic DDPG for Robot Action Space Decomposition: A Framework to Control Large 3D Deformation of Soft Linear Objects](https://mlsanity.com/paper/2312.04308/) (2023)
- [FootstepNet: an Efficient Actor-Critic Method for Fast On-line Bipedal Footstep Planning and Forecasting](https://mlsanity.com/paper/2403.12589/) (2024)
- [Using Deep Reinforcement Learning with Automatic Curriculum Learning for Mapless Navigation in Intralogistics](https://mlsanity.com/paper/2202.11512/) (2022)
- [Towards Safe Maneuvering of Double-Ackermann-Steering Robots with a Soft Actor-Critic Framework](https://mlsanity.com/paper/2510.10332/) (2025)

## Built on by (most cited first, 1 of 1)

- [DRL-Based Pose Control for Double-Ackermann Robots Under Actuation Uncertainties](https://mlsanity.com/paper/2606.00313/) (2026)

## Abstract (arXiv)

Autonomous control of double-Ackermann-steering robots is essential in agricultural applications, where robots must execute precise and complex maneuvers within a limited space. Classical methods, such as the Timed Elastic Band (TEB) planner, can address this problem, but they rely on parameter tuning, making them highly sensitive to changes in robot configuration or environment and impractical to deploy without constant recalibration. At the same time, end-to-end deep reinforcement learning (DRL) methods often fail due to unsuitable reward functions for non-holonomic constraints, resulting in sub-optimal policies and poor generalization. To address these challenges, this paper presents ManeuverNet, a DRL framework tailored for double-Ackermann systems, combining Soft Actor-Critic with CrossQ. Furthermore, ManeuverNet introduces four specifically designed reward functions to support maneuver learning. Unlike prior work, ManeuverNet does not depend on expert data or handcrafted guidance. We extensively evaluate ManeuverNet against both state-of-the-art DRL baselines and the TEB planner. Experimental results demonstrate that our framework substantially improves maneuverability and success rates, achieving more than a 40% gain over DRL baselines. Moreover, ManeuverNet effectively mitigates the strong parameter sensitivity observed in the TEB planner. In real-world trials, ManeuverNet achieved up to a 90% increase in maneuvering trajectory efficiency, highlighting its robustness and practical applicability.