Uncertainty-Aware Visual Perception for Safe Motion Planning

by   Ralf Römer, et al.

For safe operation, a robot must be able to avoid collisions in uncertain environments. Existing approaches for motion planning with uncertainties often make conservative assumptions about Gaussianity and the obstacle geometry. While visual perception can deliver a more accurate representation of the environment, its use for safe motion planning is limited by the inherent miscalibration of neural networks and the challenge of obtaining adequate datasets. In order to address these imitations, we propose to employ ensembles of deep semantic segmentation networks trained with systematically augmented datasets to ensure reliable probabilistic occupancy information. For avoiding conservatism during motion planning, we directly employ the probabilistic perception via a scenario-based path planning approach. A velocity scheduling scheme is applied to the path to ensure a safe motion despite tracking inaccuracies. We demonstrate the effectiveness of the systematic data augmentation in combination with deep ensembles and the proposed scenario-based planning approach in comparisons to state-of-the-art methods and validate our framework in an experiment involving a human hand.


page 2

page 4

page 6

page 21

page 23

page 29

page 33

page 34


Capture Uncertainties in Deep Neural Networks for Safe Operation of Autonomous Driving Vehicles

Uncertainties in Deep Neural Network (DNN)-based perception and vehicle'...

Learning Obstacle Representations for Neural Motion Planning

Motion planning and obstacle avoidance is a key challenge in robotics ap...

Simultaneous Scene Reconstruction and Whole-Body Motion Planning for Safe Operation in Dynamic Environments

Recent work has demonstrated real-time mapping and reconstruction from d...

Safe motion planning with environment uncertainty

We present an approach for safe motion planning under robot state and en...

Safe Motion Planning against Multimodal Distributions based on a Scenario Approach

We present the design of a motion planning algorithm that ensures safety...

Tackling Existence Probabilities of Objects with Motion Planning for Automated Urban Driving

Motion planners take uncertain information about the environment as an i...

Safe Motion Planning in Unknown Environments: Optimality Benchmarks and Tractable Policies

This paper addresses the problem of planning a safe (i.e., collision-fre...

Please sign up or login with your details

Forgot password? Click here to reset