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

Tai, Lei; Zhang, Jingwei; Liu, Ming; Burgard, Wolfram

doi:10.1109/icra.2018.8460968

Cited by 178 publications

(107 citation statements)

References 16 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other deep RL approaches [5], [11], [12] learn to select actions directly from raw sensor readings (either 2D laserscans or images) with end-to-end training. The raw sensor approach has the advantage that both static and dynamic obstacles (including walls) can be fed into the network with a single framework.…”

Section: A Related Workmentioning

confidence: 99%

Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning

Everett

Chen

How

2018

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

487

295

View full text Add to dashboard Cite

Robots that navigate among pedestrians use collision avoidance algorithms to enable safe and efficient operation. Recent works present deep reinforcement learning as a framework to model the complex interactions and cooperation. However, they are implemented using key assumptions about other agents' behavior that deviate from reality as the number of agents in the environment increases. This work extends our previous approach to develop an algorithm that learns collision avoidance among a variety of types of dynamic agents without assuming they follow any particular behavior rules. This work also introduces a strategy using LSTM that enables the algorithm to use observations of an arbitrary number of other agents, instead of previous methods that have a fixed observation size. The proposed algorithm outperforms our previous approach in simulation as the number of agents increases, and the algorithm is demonstrated on a fully autonomous robotic vehicle traveling at human walking speed, without the use of a 3D Lidar.

show abstract

Section: A Related Workmentioning

confidence: 99%

Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning

Everett

Chen

How

2018

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

487

295

View full text Add to dashboard Cite

show abstract

“…In addition, Kuefler et al [6] presented an approach based on Generative Adversarial Imitation Learning (GAIL) [18], where they learn driver models for an autonomous car based on expert demonstrations. Tai et al [19] recently applied GAIL to model interaction-aware navigation behavior. Although conceptually GAIL generalizes better than standard behavioral cloning techniques, it is still constrained by the provided expert demonstrations.…”

Section: A Learning By Demonstrationmentioning

confidence: 99%

Reinforced Imitation: Sample Efficient Deep Reinforcement Learning for Mapless Navigation by Leveraging Prior Demonstrations

Pfeiffer

Shukla

Turchetta

et al. 2018

IEEE Robot. Autom. Lett.

157

View full text Add to dashboard Cite

This work presents a case study of a learning-based approach for target driven map-less navigation. The underlying navigation model is an end-to-end neural network which is trained using a combination of expert demonstrations, imitation learning (IL) and reinforcement learning (RL). While RL and IL suffer from a large sample complexity and the distribution mismatch problem, respectively, we show that leveraging prior expert demonstrations for pre-training can reduce the training time to reach at least the same level of performance compared to plain RL by a factor of 5. We present a thorough evaluation of different combinations of expert demonstrations, different RL algorithms and reward functions, both in simulation and on a real robotic platform. Our results show that the final model outperforms both standalone approaches in the amount of successful navigation tasks. In addition, the RL reward function can be significantly simplified when using pre-training, e.g. by using a sparse reward only. The learned navigation policy is able to generalize to unseen and real-world environments.

show abstract

“…According to their result, it is desirable for the robot to keep more than 3.5 m away from the pedestrian, as shown in Figure 1b. Thus, a number of methods for navigating a robot considering the social distance from humans have been presented [11,21,[26][27][28][29][30].…”

Section: Robot Navigation Considering the Social Distancementioning

confidence: 99%

A Pedestrian Avoidance Method Considering Personal Space for a Guide Robot

Hiroi

Ito

2019

Robotics

View full text Add to dashboard Cite

Many methods have been proposed for avoiding obstacles in robotic systems. However, a robotic system that moves without colliding with obstacles and people, while still being mentally safe to the persons nearby, has not yet been realized. In this paper, we describe the development of a method for a mobile robot to avoid a pedestrian approaching from the front and to pass him/her by while preserving the “public distance” of personal space. We assume a robot that moves along a prerecorded path. When the robot detects a pedestrian using a laser range finder (LRF), it calculates the trajectory to avoid the pedestrian considering their personal space, passes by the pedestrian, and returns to the original trajectory. We introduce a virtual target to control the robot moving along the path, such that it can use the same control strategy as for human-following behavior. We carry out experiments to evaluate the method along three routes, in which the robot functioned without problems. The distance between the robot and the pedestrian was 9.3 m, on average, when the robot started to use avoiding behavior, which is large enough to keep a public distance from a pedestrian. When the robot passed by the pedestrian, the minimum distance between them was 1.19 m, which was large enough for passing safely.

show abstract

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

Cited by 178 publications

References 16 publications

Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning

Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning

Reinforced Imitation: Sample Efficient Deep Reinforcement Learning for Mapless Navigation by Leveraging Prior Demonstrations

A Pedestrian Avoidance Method Considering Personal Space for a Guide Robot

Contact Info

Product

Resources

About