Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

A review of smart homes-Present state and future challenges

In this work we describe an autonomous soft-bodied robot that is both self-contained and capable of rapid, continuum-body motion. We detail the design, modeling, fabrication, and control of the soft fish, focusing on enabling the robot to perform rapid escape responses. The robot employs a compliant body with embedded actuators emulating the slender anatomical form of a fish. In addition, the robot has a novel fluidic actuation system that drives body motion and has all the subsystems of a traditional robot onboard: power, actuation, processing, and control. At the core of the fish's soft body is an array of fluidic elastomer actuators. We design the fish to emulate escape responses in addition to forward swimming because such maneuvers require rapid body accelerations and continuum-body motion. These maneuvers showcase the performance capabilities of this self-contained robot. The kinematics and controllability of the robot during simulated escape response maneuvers are analyzed and compared wit...

/pdf/autonomous-soft-robotic-fish-capable-of-escape-maneuvers-4w5jc261h9.pdf

Autonomous Soft Robotic Fish Capable of Escape Maneuvers Using Fluidic Elastomer Actuators.

Bag of visual words and fusion methods for action recognition

We address action recognition in videos by modeling the spatial-temporal structures of human poses. We start by improving a state of the art method for estimating human joint locations from videos. More precisely, we obtain the K-best estimations output by the existing method and incorporate additional segmentation cues and temporal constraints to select the ``best'' one. Then we group the estimated joints into five body parts (e.g. the left arm) and apply data mining techniques to obtain a representation for the spatial-temporal structures of human actions. This representation captures the spatial configurations of body parts in one frame (by spatial-part-sets) as well as the body part movements(by temporal-part-sets) which are characteristic of human actions. It is interpretable, compact, and also robust to errors on joint estimations. Experimental results first show that our approach is able to localize body joints more accurately than existing methods. Next we show that it outperforms state of the art action recognizers on the UCF sport, the Keck Gesture and the MSR-Action3D datasets.

/pdf/an-approach-to-pose-based-action-recognition-4phunghcoj.pdf

An Approach to Pose-Based Action Recognition

Mobile manipulators derive significant novel capabilities for enhanced interactions with the world by merging mobility with manipulation. However, a careful resolution of the redundancy and active control of the reconfigurability, created by the surplus articulated DOFs and actuation, are the keys to unlocking this potential. Nonholonomic wheeled mobile manipulators, formed by mounting manipulator arms on disc-wheeled mobile bases, are a small but important subclass of mobile manipulators. The primary control challenges arise due to the dynamic-level coupling of the nonholonomy of the wheeled mobile bases with the inherent kinematic and actuation redundancy within the articulated chain. The solution approach in this paper builds upon a dynamically consistent and decoupled partitioning of the articulated system dynamics between the external (task) space and internal (null) space. The independent controllers, developed within each decoupled space, facilitate active internal reconfiguration, in addition to resolving redundancy at the dynamic level. Specifically, two variants of null-space controllers are implemented to improve disturbance rejection and active reconfiguration during performance of end-effector tasks by a primary end-effector impedance mode controller. These algorithms are evaluated within an implementation framework that emphasizes both virtual prototyping and hardware-in-the-loop testing with representative case studies.

Experimental Evaluation of Dynamic Redundancy Resolution in a Nonholonomic Wheeled Mobile Manipulator

A proof-of-concept prototype wheelchair with legs for people with motor disabilities is proposed, with the objective of demonstrating the feasibility of a completely new approach to mobility. The authors' prototype system consists of a chair equipped with wheels and legs, and is capable of traversing uneven terrain and circumventing obstacles. The important design considerations, the system design and analysis, and an experimental prototype of a chair are discussed. The results from the analysis and experimentation show the feasibility of the proposed concept and its advantages.

/pdf/design-of-a-wheelchair-with-legs-for-people-with-motor-46lr1lijau.pdf

Design of a wheelchair with legs for people with motor disabilities

This paper presents a differential-flatness-based integrated point-to-point trajectory planning and control method for a class of nonholonomic wheeled mobile manipulator (WMM). We demonstrate that its kinematic model possesses a feedback-linearizable description due to the flatness property, which allows for full-state controllability. Trajectory planning can then be simplified and achieved by polynomial fitting method in the flat output space to satisfy the terminal conditions, while control design reduces to a pole-placement problem for a linear system. The method is then deployed on our custom-constructed WMM hardware to evaluate its effectiveness and to highlight various aspects of the hardware implementation.

Differential-Flatness-Based Planning and Control of a Wheeled Mobile Manipulator—Theory and Experiment

Wheeled Mobile Manipulators (WMM) possess many advantages over fixed-base counterparts in terms of improved workspace, mobility and robustness. However, the combination of the nonholonomic constraints with the inherent redundancy limits effective exploitation of end-effector payload manipulation capabilities. The dynamic-level redundancy-resolution scheme presented in this paper decomposes the system dynamics into decoupled task-space (end-effector motions/forces) and a dynamically consistent null-space (internal motions/forces) component. This simplifies the subsequent development of a prioritized task-space control (of end-effector interactions) and a decoupled but secondary null-space control (of internal motions) in a hierarchical WMM controller. Various aspects of the ensuing novel capabilities are illustrated using a series of simulation results.

https://www.cambridge.org/core/services/aop-cambridge-core/content/view/S0263574706003328

Dynamic redundancy resolution in a nonholonomic wheeled mobile manipulator

The rising popularity of self-driving cars has led to the emergence of a new research field in recent years: Autonomous racing. Researchers are developing software and hardware for high-performance race vehicles which aim to operate autonomously on the edge of the vehicle’s limits: High speeds, high accelerations, low reaction times, highly uncertain, dynamic, and adversarial environments. This paper represents the first holistic survey that covers the research in the field of autonomous racing. We focus on the field of autonomous racecars only and display the algorithms, methods, and approaches used in the areas of perception, planning, control, and end-to-end learning. Further, with an increasing number of autonomous racing competitions, researchers now have access to high-performance platforms to test and evaluate their autonomy algorithms. This survey presents a comprehensive overview of the current autonomous racing platforms, emphasizing the software-hardware co-evolution to the current stage. Finally, based on additional discussion with leading researchers in the field, we conclude with a summary of open research challenges that will guide future researchers in this field.

Venkat Krovi

Papers

Experimental Evaluation of Dynamic Redundancy Resolution in a Nonholonomic Wheeled Mobile Manipulator

Design of a wheelchair with legs for people with motor disabilities

Differential-Flatness-Based Planning and Control of a Wheeled Mobile Manipulator—Theory and Experiment

Dynamic redundancy resolution in a nonholonomic wheeled mobile manipulator

Autonomous Vehicles on the Edge: A Survey on Autonomous Vehicle Racing