# Vision-Proprioception Fusion with Mamba2 in End-to-End Reinforcement Learning for Motion Control

arXiv: https://arxiv.org/abs/2509.07593 · HTML: https://mlsanity.com/paper/2509.07593/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 29 of its 50 references that are in the map.
- First posted on arXiv 9 Sep 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Video, motion and generative Mamba models](https://mlsanity.com/ssm/video-motion-and-generative-mamba-models/)
- 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, 29 of 29)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [An Introduction to Convolutional Neural Networks](https://mlsanity.com/paper/1511.08458/) (2015)
- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [Learning agile and dynamic motor skills for legged robots](https://mlsanity.com/paper/1901.08652/) (2019)
- [Sim-to-Real: Learning Agile Locomotion For Quadruped Robots](https://mlsanity.com/paper/1804.10332/) (2018)
- [Active Domain Randomization](https://mlsanity.com/paper/1904.04762/) (2019)
- [Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots](https://mlsanity.com/paper/2103.14295/) (2021)
- [FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mamba](https://mlsanity.com/paper/2404.09498/) (2024)
- [Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers](https://mlsanity.com/paper/2107.03996/) (2021)
- [Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotion](https://mlsanity.com/paper/2011.02404/) (2020)
- [Learning Vision-Based Bipedal Locomotion for Challenging Terrain](https://mlsanity.com/paper/2309.14594/) (2023)
- [Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision](https://mlsanity.com/paper/2504.02477/) (2025)
- [GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model](https://mlsanity.com/paper/2104.09771/) (2021)
- [Hierarchical Reinforcement Learning for Quadruped Locomotion](https://mlsanity.com/paper/1905.08926/) (2019)
- [Feedback MPC for Torque-Controlled Legged Robots](https://mlsanity.com/paper/1905.06144/) (2019)
- [World Model-based Perception for Visual Legged Locomotion](https://mlsanity.com/paper/2409.16784/) (2024)
- [AlignMamba: Enhancing Multimodal Mamba with Local and Global Cross-modal Alignment](https://mlsanity.com/paper/2412.00833/) (2024)
- [DepMamba: Progressive Fusion Mamba for Multimodal Depression Detection](https://mlsanity.com/paper/2409.15936/) (2024)
- [A Survey on Mamba Architecture for Vision Applications](https://mlsanity.com/paper/2502.07161/) (2025)
- [ViTAL: Vision-Based Terrain-Aware Locomotion for Legged Robots](https://mlsanity.com/paper/2212.01246/) (2022)
- [Accelerating Model Predictive Control for Legged Robots through Distributed Optimization](https://mlsanity.com/paper/2403.11742/) (2024)
- [Guided Reinforcement Learning for Omnidirectional 3D Jumping in Quadruped Robots](https://mlsanity.com/paper/2507.16481/) (2025)
- [LocoMamba: Vision-Driven Locomotion via End-to-End Deep Reinforcement Learning with Mamba](https://mlsanity.com/paper/2508.11849/) (2025)
- [Adaptive Non-linear Centroidal MPC with Stability Guarantees for Robust Locomotion of Legged Robots](https://mlsanity.com/paper/2409.01144/) (2024)
- [QuadKAN: KAN-Enhanced Quadruped Motion Control via End-to-End Reinforcement Learning](https://mlsanity.com/paper/2508.19153/) (2025)

## Abstract (arXiv)

End-to-end reinforcement learning (RL) for motion control trains policies directly from sensor inputs to motor commands, enabling unified controllers for different robots and tasks. However, most existing methods are either blind (proprioception-only) or rely on fusion backbones with unfavorable compute-memory trade-offs. Recurrent controllers struggle with long-horizon credit assignment, and Transformer-based fusion incurs quadratic cost in token length, limiting temporal and spatial context. We present a vision-driven cross-modal RL framework built on SSD-Mamba2, a selective state-space backbone that applies state-space duality (SSD) to enable both recurrent and convolutional scanning with hardware-aware streaming and near-linear scaling. Proprioceptive states and exteroceptive observations (e.g., depth tokens) are encoded into compact tokens and fused by stacked SSD-Mamba2 layers. The selective state-space updates retain long-range dependencies with markedly lower latency and memory use than quadratic self-attention, enabling longer look-ahead, higher token resolution, and stable training under limited compute. Policies are trained end-to-end under curricula that randomize terrain and appearance and progressively increase scene complexity. A compact, state-centric reward balances task progress, energy efficiency, and safety. Across diverse motion-control scenarios, our approach consistently surpasses strong state-of-the-art baselines in return, safety (collisions and falls), and sample efficiency, while converging faster at the same compute budget. These results suggest that SSD-Mamba2 provides a practical fusion backbone for resource-constrained robotic and autonomous systems in engineering informatics applications.