Multiplicative Controller Fusion: A Hybrid Navigation Strategy For Deployment in Unknown Environments

by   Krishan Rana, et al.

Learning-based approaches often outperform hand-coded algorithmic solutions for many problems in robotics. However, learning long-horizon tasks on real robot hardware can be intractable, and transferring a learned policy from simulation to reality is still extremely challenging. We present a novel approach to model-free reinforcement learning that can leverage existing sub-optimal solutions as an algorithmic prior during training and deployment. During training, our gated fusion approach enables the prior to guide the initial stages of exploration, increasing sample-efficiency and enabling learning from sparse long-horizon reward signals. Importantly, the policy can learn to improve beyond the performance of the sub-optimal prior since the prior's influence is annealed gradually. During deployment, the policy's uncertainty provides a reliable strategy for transferring a simulation-trained policy to the real world by falling back to the prior controller in uncertain states. We show the efficacy of our Multiplicative Controller Fusion approach on the task of robot navigation and demonstrate safe transfer from simulation to the real world without any fine tuning. The code for this project is made publicly available at


page 1

page 6

page 7


Bayesian Controller Fusion: Leveraging Control Priors in Deep Reinforcement Learning for Robotics

We present Bayesian Controller Fusion (BCF): a hybrid control strategy t...

Residual Reactive Navigation: Combining Classical and Learned Navigation Strategies For Deployment in Unknown Environments

In this work we focus on improving the efficiency and generalisation of ...

Sim-to-Real Transfer with Incremental Environment Complexity for Reinforcement Learning of Depth-Based Robot Navigation

Transferring learning-based models to the real world remains one of the ...

Sim-to-Real Deep Reinforcement Learning with Manipulators for Pick-and-place

When transferring a Deep Reinforcement Learning model from simulation to...

Learning Observation-Based Certifiable Safe Policy for Decentralized Multi-Robot Navigation

Safety is of great importance in multi-robot navigation problems. In thi...

Robust Feedback Motion Policy Design Using Reinforcement Learning on a 3D Digit Bipedal Robot

In this paper, a hierarchical and robust framework for learning bipedal ...

Please sign up or login with your details

Forgot password? Click here to reset