Chin-Kai Chang

Mobile robot vision navigation & localization using Gist and Saliency

We present a vision-based navigation and localization system using two biologically-inspired scene understanding models which are studied from human visual capabilities: (1) Gist model which captures the holistic characteristics and layout of an image and (2) Saliency model which emulates the visual attention of primates to identify conspicuous regions in the image. Here the localization system utilizes the gist features and salient regions to accurately localize the robot, while the navigation system uses the salient regions to perform visual feedback control to direct its heading and go to a user-provided goal location. We tested the system on our robot, Beobot2.0, in an indoor and outdoor environment with a route length of 36.67m (10,890 video frames) and 138.27m (28,971 frames), respectively. On average, the robot is able to drive within 3.68cm and 8.78cm (respectively) of the center of the lane.

Mobile robot monocular vision navigation based on road region and boundary estimation

We present a monocular vision-based navigation system that incorporates two contrasting approaches: region segmentation that computes the road appearance, and road boundary detection that estimates the road shape. The former approach segments the image into multiple regions, then selects and tracks the most likely road appearance. On the other hand, the latter detects the vanishing point and road boundaries to estimate the shape of the road. Our algorithm operates in urban road settings and requires no training or camera calibration to maximize its adaptability to many environments. We tested our system in 1 indoor and 3 outdoor urban environments using our ground-based robot, Beobot 2.0, for real-time autonomous visual navigation. In 20 trial runs the robot was able to travel autonomously for 98.19% of the total route length of 316.60m.

Mobile robot navigation system in outdoor pedestrian environment using vision-based road recognition

We present a mobile robot navigation system guided by a novel vision-based road recognition approach. The system represents the road as a set of lines extrapolated from the detected image contour segments. These lines enable the robot to maintain its heading by centering the vanishing point in its field of view, and to correct the long term drift from its original lateral position. We integrate odometry and our visual road recognition system into a grid-based local map that estimates the robot pose as well as its surroundings to generate a movement path. Our road recognition system is able to estimate the road center on a standard dataset with 25,076 images to within 11.42 cm (with respect to roads at least 3 m wide). It outperforms three other state-of-the-art systems. In addition, we extensively test our navigation system in four busy college campus environments using a wheeled robot. Our tests cover more than 5 km of autonomous driving without failure. This demonstrates robustness of the proposed approach against challenges that include occlusion by pedestrians, non-standard complex road markings and shapes, shadows, and miscellaneous obstacle objects.

Beobot 2.0: Cluster architecture for mobile robotics

With the recent proliferation of robust but computationally demanding robotic algorithms, there is now a need for a mobile robot platform equipped with powerful computing facilities. In this paper, we present the design and implementation of Beobot 2.0, an affordable research-level mobile robot equipped with a cluster of 16 2.2-GHz processing cores. Beobot 2.0 uses compact Computer on Module (COM) processors with modest power requirements, thus accommodating various robot design constraints while still satisfying the requirement for computationally intensive algorithms. We discuss issues involved in utilizing multiple COM Express modules on a mobile platform, such as interprocessor communication, power consumption, cooling, and protection from shocks, vibrations, and other environmental hazards such as dust and moisture. We have applied Beobot 2.0 to the following computationally demanding tasks: laser-based robot navigation, scale-invariant feature transform (SIFT) object recognition, finding objects in a cluttered scene using visual saliency, and vision-based localization, wherein the robot has to identify landmarks from a large database of images in a timely manner. For the last task, we tested the localization system in three large-scale outdoor environments, which provide 3,583, 6,006, and 8,823 test frames, respectively. The localization errors for the three environments were 1.26, 2.38, and 4.08 m, respectively. The per-frame processing times were 421.45, 794.31, and 884.74 ms respectively, representing speedup factors of 2.80, 3.00, and 3.58 when compared to a single dual-core computer performing localization.

Learning to Recognize Objects by Retaining Other Factors of Variation

Most ConvNets formulate object recognition from natural images as a single task classification problem, and attempt to learn features useful for object categories, but invariant to other factors of variation such as pose and illumination. They do not explicitly learn these other factors, instead, they usually discard them by pooling and normalization. Here, we take the opposite approach: we train ConvNets for object recognition by retaining other factors (pose in our case) and learning them jointly with object category. We design a new multi-task leaning (MTL) ConvNet, named disentangling CNN (disCNN), which explicitly enforces the disentangled representations of object identity and pose, and is trained to predict object categories and pose transformations. disCNN achieves significantly better object recognition accuracies than the baseline CNN trained solely to predict object categories on the iLab-20M dataset, a large-scale turntable dataset with detailed pose and lighting information. We further show that the pretrained features on iLab-20M generalize to both Washington RGB-D and ImageNet datasets, and the pretrained dis-CNN features are significantly better than the pretrained baseline CNN features for fine-tuning on ImageNet.

Beobot 2.0: Autonomous mobile robot localization and navigation in outdoor pedestrian environment

We present Beobot 2.0 [1], an autonomous mobile robot designed to operate in unconstrained urban environments. The goal of the project is to create service robots that can be deployed for various tasks that require long range travel. Over the past two years, Beobot has successfully traversed various paths across the USC campus, demonstrating its robustness in recognizing and following different types of roads, avoiding obstacles such as pedestrians and service vehicles, and finding its way to the goal.