Perception

//Perception

Choosing Where To Go: Complete 3D Exploration With Stereo

This paper is about the autonomous acquisition of detailed 3D maps of a-priori unknown environments using a stereo camera - it is about choosing where to go. Our approach hinges upon a boundary value constrained partial differential equation (PDE) – the solution of which provides a scalar field guaranteed to have no local minima. This [...]

Choosing Where To Go: Complete 3D Exploration With Stereo2016-10-22T19:51:02+01:00

Hidden View Synthesis using Real-Time Visual SLAM for Simplifying Video Surveillance Analysis

Abstract— Understanding and analysing static or mobile surveillance cameras often requires knowledge of the scene and the camera placement. In this article, we provide a way to simplify the user’s task of understanding the scene by rendering the camera view as if observed from the user’s perspective by estimating his position using a real-time visual [...]

Hidden View Synthesis using Real-Time Visual SLAM for Simplifying Video Surveillance Analysis2016-10-22T19:51:02+01:00

Risky Planning: Path Planning over Costmaps with a Probabilistically Bounded Speed-Accuracy Tradeoff

Abstract— This paper is about generating plans over uncertain maps quickly. Our approach combines the ALT (A* search, landmarks and the triangle inequality) algorithm and risk heuristics to guide search over probabilistic cost maps. We build on previous work which generates probabilistic cost maps from aerial imagery and use these cost maps to precompute heuristics [...]

Risky Planning: Path Planning over Costmaps with a Probabilistically Bounded Speed-Accuracy Tradeoff2016-10-22T19:51:02+01:00

Self Help: Seeking Out Perplexing Images for Ever Improving Navigation

Abstract—This paper is a demonstration of how a robot can, through introspection and then targeted data retrieval, improve its own performance. It is a step in the direction of lifelong learning and adaptation and is motivated by the desire to build robots that have plastic competencies which are not baked in. They should react to [...]

Self Help: Seeking Out Perplexing Images for Ever Improving Navigation2016-10-22T19:51:02+01:00

Planning to Perceive: Exploiting Mobility For Robust Object Detection

Abstract - Consider the task of a mobile robot autonomously navigating through an environment while detecting and mapping objects of interest using a noisy object detector. The robot must reach its destination in a timely manner, but is rewarded for correctly detecting recognizable objects to be added to the map, and penalized for false alarms. However, [...]

Planning to Perceive: Exploiting Mobility For Robust Object Detection2016-10-22T19:51:02+01:00

Non-parametric Learning for Natural Plan Generation

We present a novel way to learn sampling distributions for sampling-based motion planners by making use of expert data. We learn an estimate (in a non-parametric setting) of sample densities around semantic regions of interest, and incorporate these learned distributions into a sampling-based planner to produce natural plans. Our motivation is that certain aspects of [...]

Non-parametric Learning for Natural Plan Generation2016-10-22T19:51:02+01:00

Planning Most-Likely Paths from Overhead Imagery

In this work, we are concerned with planning paths from overhead imagery. The novelty here lies in taking explicit account of uncertainty in terrain classification and spatial variation in terrain cost. The image is first classified using a multi-class Gaussian Process Classifier which provides probabilities of class membership at each location in the image, which is then combined [...]

Planning Most-Likely Paths from Overhead Imagery2016-10-22T19:51:02+01:00

Semantic Categorization of Outdoor Scenes with Uncertainty Estimates using Multi-Class Gaussian Process Classification

Abstract— This paper presents a novel semantic categorization method for 3D point cloud data using supervised, multi-class Gaussian Process (GP) classification. In contrast to other approaches, and particularly Support Vector Machines, which probably are the most used method for this task to date, GPs have the major advantage of providing informative uncertainty estimates about the [...]

Semantic Categorization of Outdoor Scenes with Uncertainty Estimates using Multi-Class Gaussian Process Classification2016-10-22T19:51:02+01:00

Teaching a Randomized Planner to plan with Semantic fields

 Abstract—This paper presents a novel way to bias the sampling domain of stochastic planners by learning from example plans. We learn a generative model of a planner as a function of proximity to labeled objects in the workspace. Our motivation is that certain objects in the workspace have a local influence on planning strategies, which [...]

Teaching a Randomized Planner to plan with Semantic fields2018-06-20T15:28:29+01:00