Socially Compliant Navigation Through Raw Depth Inputs with Generative Adversarial Imitation Learning

By Lei Tai, Jingwei Zhang, Ming Liu, Wolfram Burgard. 2017

206 citations recorded by the source corpus.

We present an approach for mobile robots to learn to navigate in dynamic environments with pedestrians via raw depth inputs, in a socially compliant manner. To achieve this, we adopt a generative adversarial imitation learning (GAIL) strategy, which improves upon a pre-trained behavior cloning policy. Our approach overcomes the disadvantages of previous methods, as they heavily depend on the full knowledge of the location and velocity information of nearby pedestrians, which not only requires specific sensors, but also the extraction of such state information from raw sensory input could consume much computation time. In this paper, our proposed GAIL-based model performs directly on raw depth inputs and plans in real-time. Experiments show that our GAIL-based approach greatly improves the safety and efficiency of the behavior of mobile robots from pure behavior cloning. The real-world deployment also shows that our method is capable of guiding autonomous vehicles to navigate in a socially compliant manner directly through raw depth inputs. In addition, we release a simulation plugin for modeling pedestrian behaviors based on the social force model.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Ocean Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Ocean Engineering

Citations in the corpus

A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation (2016, positive): “Tai et al. (2018) learn a socially compliant navigation policy through GAIL, based on raw depth input, and demonstrate the learned behaviors in real robotics experiments.”
One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning (2018, background): “] and Tow et al. [53] learn a model that predicts the outcome of the human’s demonstration from a particular scene. Similarly, other works have learned a reward function based on human demonstrations [47, 49, 26, 46, 50]. Once the system has learned about the reward function or desired outcome under”
Deep Local Trajectory Replanning and Control for Robot Navigation (2019, methodology): “[41] and Müller et al.”
Core Challenges of Social Robot Navigation: A Survey (2021, methodology): “, imitation learning [237]—we would likewise expect data needs to reflect state space complexity.”
Reinforced Imitation: Sample Efficient Deep Reinforcement Learning for Mapless Navigation by Leveraging Prior Demonstrations (2018, methodology): “[19] recently applied GAIL to model interaction-aware navigation behavior.”
VR-Goggles for Robots: Real-to-Sim Domain Adaptation for Visual Control (2018, background): “For example, 2D Lidar [15]–[17] and depth images [18], [19] are sometimes chosen as the sensor modality, since the discrepancies between the simulated domain and the real-world domain for them can be”