A deep-network solution towards model-less obstacle avoidance

Tai, Lei; Li, Shaohua; Liu, Ming

doi:10.1109/iros.2016.7759428

Cited by 178 publications

(116 citation statements)

References 11 publications

Supporting

Mentioning

116

Contrasting

Order By: Relevance

“…Although there are other approaches introduced in the literature including deep learning approaches [18,19] and senor-based analyses [20], these works are not relevant to our work as they use a vision-based model. They use a set of indoor depth data-sets for training, where the ground-truth output is instructed by a human operator.…”

Section: Discussionmentioning

confidence: 99%

An Optimal and Energy Efficient Multi-Sensor Collision-Free Path Planning Algorithm for a Mobile Robot in Dynamic Environments

et al. 2017

View full text Add to dashboard Cite

There has been a remarkable growth in many different real-time systems in the area of autonomous mobile robots. This paper focuses on the collaboration of efficient multi-sensor systems to create new optimal motion planning for mobile robots. A proposed algorithm is used based on a new model to produce the shortest and most energy-efficient path from a given initial point to a goal point. The distance and time traveled, in addition to the consumed energy, have an asymptotic complexity of O(nlogn), where n is the number of obstacles. Real time experiments are performed to demonstrate the accuracy and energy efficiency of the proposed motion planning algorithm.

show abstract

Section: Discussionmentioning

confidence: 99%

An Optimal and Energy Efficient Multi-Sensor Collision-Free Path Planning Algorithm for a Mobile Robot in Dynamic Environments

et al. 2017

View full text Add to dashboard Cite

show abstract

“…As is shown in table 2, Lei Tai et al tested deep-network solution towards obstacle avoidance in an indoor environment, their overall accuracy is 80.2% [13]. Comparing their method and result, our test was designed in the indoor environment with mark and without mark, respectively.…”

Section: Comparisonmentioning

confidence: 98%

CNN-Based Vision Model for Obstacle Avoidance of Mobile Robot

et al. 2017

View full text Add to dashboard Cite

Abstract. Exploration in a known or unknown environment for a mobile robot is an essential application. In the paper, we study the mobile robot obstacle avoidance problem in an indoor environment. We present an end-to-end learning model based Convolutional Neural Network (CNN), which takes the raw image obtained from camera as only input. And the method converts directly the raw pixels to steering commands including turn left, turn right and go straight. Training data was collected by a human remotely controlled mobile robot which was manipulated to explore in a structure environment without colliding into obstacles. Our neural network was trained under caffe framework and specific instructions are executed by the Robot Operating System (ROS). We analysis the effect of the datasets from different environments with some marks on training process and several real-time detect experiments were designed. The final test result shows that the accuracy can be improved by increase the marks in a structured environment and our model can get high accuracy on obstacle avoidance for mobile robots.

show abstract

“…Instead, IVOA predicts where in the input space the failure will happen and what type the failure will be. It should be noted that IVOA is distinct from works such as [7], [8], [9] that use only a black box model for the purpose of obstacle avoidance. It instead relies on a modelbased stereo obstacle detection at the core and accompanies that with a black box model that provides predictions of failure cases of the former along with an uncertainty estimate of the predictions.…”

Section: Related Workmentioning

confidence: 99%

IVOA: Introspective Vision for Obstacle Avoidance

Rabiee

Biswas

2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Vision, as an inexpensive yet information rich sensor, is commonly used for perception on autonomous mobile robots. Unfortunately, accurate vision-based perception requires a number of assumptions about the environment to hold -some examples of such assumptions, depending on the perception algorithm at hand, include purely lambertian surfaces, texture-rich scenes, absence of aliasing features, and refractive surfaces. In this paper, we present an approach for introspective vision for obstacle avoidance (IVOA) -by leveraging a supervisory sensor that is occasionally available, we detect failures of stereo vision-based perception from divergence in plans generated by vision and the supervisory sensor. By projecting the 3D coordinates where the plans agree and disagree onto the images used for vision-based perception, IVOA generates a training set of reliable and unreliable image patches for perception. We then use this training dataset to learn a model of which image patches are likely to cause failures of the vision-based perception algorithm. Using this model, IVOA is then able to predict whether the relevant image patches in the observed images are likely to cause failures due to vision (both false positives and false negatives). We empirically demonstrate with extensive real-world data from both indoor and outdoor environments, the ability of IVOA to accurately predict the failures of two distinct vision algorithms.

show abstract

A deep-network solution towards model-less obstacle avoidance

Cited by 178 publications

References 11 publications

An Optimal and Energy Efficient Multi-Sensor Collision-Free Path Planning Algorithm for a Mobile Robot in Dynamic Environments

An Optimal and Energy Efficient Multi-Sensor Collision-Free Path Planning Algorithm for a Mobile Robot in Dynamic Environments

CNN-Based Vision Model for Obstacle Avoidance of Mobile Robot

IVOA: Introspective Vision for Obstacle Avoidance

Contact Info

Product

Resources

About