NeoNav: Improving the Generalization of Visual Navigation via Generating Next Expected Observations

Abstract

We propose improving the cross-target and cross-scene generalization of visual navigation through learning an agent that is guided by conceiving the next observations it expects to see. This is achieved by learning a variational Bayesian model, called NeoNav, which generates the next expected observations (NEO) conditioned on the current observations of the agent and the target view. Our generative model is learned through optimizing a variational objective encompassing two key designs. First, the latent distribution is conditioned on current observations and the target view, leading to a model-based, target-driven navigation. Second, the latent space is modeled with a Mixture of Gaussians conditioned on the current observation and the next best action. Our use of mixture-of-posteriors prior effectively alleviates the issue of over-regularized latent space, thus significantly boosting the model generalization for new targets and in novel scenes. Moreover, the NEO generation models the forward dynamics of agent-environment interaction, which improves the quality of approximate inference and hence benefits data efficiency. We have conducted extensive evaluations on both real-world and synthetic benchmarks, and show that our model consistently outperforms the state-of-the-art models in terms of success rate, data efficiency, and generalization.

Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learning

“…In addition, we investigate three techniques to improve robot navigation performance in the real world, including feature space dynamics, premature collision prediction and additional target checking. We show that the proposed method significantly outperforms prior work [16], boosting the success rate from 17.5% to 28.7% and reducing approximately 16.3% of the collisions for a navigation task in the unseen scenes from the Active Vision Dataset [17]. Furthermore, we steer a wheeled robot, TurtleBot, around office scenes and show that the learned navigation policy can generalize to novel targets in unseen real-world environments.…”

“…The mapping is a surjection, which means there is only one appropriate action a t for (x t , x t+1 ). In this way, the multimodality essentially affects the generation of x t+1 , which is learned by a generative module as [16]. Generative Module.…”

“…A detailed topology of the module is pictured in Figure 3(c). Similar to [16], for alleviating the effect of data imbalance, we guarantee that approximately 1 |A| training tasks are near navigation targets, of which the optimal action is stop at the start location. We train the target checking module using a binary cross-entropy loss defined as:…”

“…Alternatives. We compare the navigation performance to the following alternative models: (1) NeoNav is our previous work [16]. (2) TD-A3C is the abbreviation of the baseline [3].…”

“…A preliminary version of the navigation model is presented in [16], which proposes a generative model for visual navigation. In this work, we have significantly extended the idea behind the model design by taking into account the multi-modality during navigation decision making, which is generally an important factor that affects the performance of navigation policy learning.…”