Anticipating human actions through recognition of object affordances and use of Anticiopatory Conditional Random Fields

December 22, 2015 20:04 ,

Koppula, H.S.; Saxena, A., Anticipating Human Activities Using Object Affordances for Reactive Robotic Response, in Pattern Analysis and Machine Intelligence, IEEE Transactions on , vol.38, no.1, pp.14-29, Jan. 1 2016, DOI: 10.1109/TPAMI.2015.2430335.

An important aspect of human perception is anticipation, which we use extensively in our day-to-day activities when interacting with other humans as well as with our surroundings. Anticipating which activities will a human do next (and how) can enable an assistive robot to plan ahead for reactive responses. Furthermore, anticipation can even improve the detection accuracy of past activities. The challenge, however, is two-fold: We need to capture the rich context for modeling the activities and object affordances, and we need to anticipate the distribution over a large space of future human activities. In this work, we represent each possible future using an anticipatory temporal conditional random field (ATCRF) that models the rich spatial-temporal relations through object affordances. We then consider each ATCRF as a particle and represent the distribution over the potential futures using a set of particles. In extensive evaluation on CAD-120 human activity RGB-D dataset, we first show that anticipation improves the state-of-the-art detection results. We then show that for new subjects (not seen in the training set), we obtain an activity anticipation accuracy (defined as whether one of top three predictions actually happened) of 84.1, 74.4 and 62.2 percent for an anticipation time of 1, 3 and 10 seconds respectively. Finally, we also show a robot using our algorithm for performing a few reactive responses.

Posted in: Computer vision , Tagged: ,

Robotic probabilistic SLAM in continuous time

December 22, 2015 19:43 ,

Furgale1 P., Tong C.-H., Barfoot T.-D., Sibley G., Continuous-time batch trajectory estimation using temporal basis functions, The International Journal of Robotics Research December 2015 vol. 34 no. 14 1688-1710, DOI: 10.1177/0278364915585860.

Roboticists often formulate estimation problems in discrete time for the practical reason of keeping the state size tractable; however, the discrete-time approach does not scale well for use with high-rate sensors, such as inertial measurement units, rolling-shutter cameras, or sweeping laser imaging sensors. The difficulty lies in the fact that a pose variable is typically included for every time at which a measurement is acquired, rendering the dimension of the state impractically large for large numbers of measurements. This issue is exacerbated for the simultaneous localization and mapping problem, which further augments the state to include landmark variables. To address this tractability issue, we propose to move the full Maximum-a-Posteriori estimation problem into continuous time and use temporal basis functions to keep the state size manageable. We present a full probabilistic derivation of the continuous-time estimation problem, derive an estimator based on the assumption that the densities and processes involved are Gaussian and show how the coefficients of a relatively small number of basis functions can form the state to be estimated, making the solution efficient. Our derivation is presented in steps of increasingly specific assumptions, opening the door to the development of other novel continuous-time estimation algorithms through the application of different assumptions at any point. We use the simultaneous localization and mapping problem as our motivation throughout the paper, although the approach is not specific to this application. Results from two experiments are provided to validate the approach: (i) self-calibration involving a camera and a high-rate inertial measurement unit, and (ii) perspective localization with a rolling-shutter camera.

Posted in: Mobile robot SLAM , Tagged:

Model checking for the verification of the correct functionality in the presence of sensor failures of a network of behaviours included in a robotic architecture

December 22, 2015 19:14 ,

Lisa Kiekbusch, Christopher Armbrust, Karsten Berns, Formal verification of behaviour networks including sensor failures, Robotics and Autonomous Systems, Volume 74, Part B, December 2015, Pages 331-339, ISSN 0921-8890, DOI: 10.1016/j.robot.2015.08.002.

The paper deals with the problem of verifying behaviour-based control systems. Although failures in sensor hardware and software can have strong influences on the robot’s operation, they are often neglected in the verification process. Instead, perfect sensing is assumed. Therefore, this paper provides an approach for modelling the sensor chain in a formal way and connecting it to the formal model of the control system. The resulting model can be verified using model checking techniques, which is shown on the examples of the control systems of an autonomous indoor robot and an autonomous off-road robot.

Posted in: Robotic architectures, Robotic software , Tagged: ,

Improvement on the classical regression-based estimation algorithm of the relative clock frequency of two remotely connected clocks for better behaviour under outliers, and a good related works section on the estimation of clock relative frequency

December 22, 2015 17:57 ,

Oka Saputra, K.; Wei-Chung Teng; Tsung-Han Chen, Hough Transform-Based Clock Skew Measurement Over Network, in Instrumentation and Measurement, IEEE Transactions on , vol.64, no.12, pp.3209-3216, Dec. 2015, DOI: 10.1109/TIM.2015.2450293.

The accurate clock skew measurement of remote devices over network connections is crucial to device fingerprinting and other related applications. Current approaches use the lower bound of offsets between the target device and the measurer to estimate clock skew; however, the accuracy of estimation is severely affected when even a few offsets appear below the crowd of offsets. This paper adopted the Hough transform to develop a new method, which searches for the densest part of the whole distribution. This method is effective in filtering out the upper and lower outliers such that the skew values derived from the remaining offsets are stable, even when lower outliers occur, or when the measuring time is not long enough for current approaches to achieve stable results. The experimental evaluation of the proposed method has been conducted in order to compare its performance with that of linear programming algorithm (LPA) and two other approaches. During the five consecutive measurements of 1000 offsets each, skews of the proposed method varied within the range of 0.59 ppm, whereas LPA resulted in the range of 0.89 ppm. Both ranges increased to 1.34 and 63.93 ppm, respectively, when the lower bounds encountered interference from lower outliers.

Notes:

  • They assume there is no NTP running in the background; however, their results seem to come from a conventional TCP/IP network, where it is difficult not to find NTP enabled.
Posted in: Communication networks, Real-Time Systems , Tagged: ,

Reinforcement learning in the automatic control area

December 22, 2015 17:41 ,

Yu Jiang; Zhong-Ping Jiang, Global Adaptive Dynamic Programming for Continuous-Time Nonlinear Systems, in Automatic Control, IEEE Transactions on , vol.60, no.11, pp.2917-2929, Nov. 2015, DOI: 10.1109/TAC.2015.2414811.

This paper presents a novel method of global adaptive dynamic programming (ADP) for the adaptive optimal control of nonlinear polynomial systems. The strategy consists of relaxing the problem of solving the Hamilton-Jacobi-Bellman (HJB) equation to an optimization problem, which is solved via a new policy iteration method. The proposed method distinguishes from previously known nonlinear ADP methods in that the neural network approximation is avoided, giving rise to significant computational improvement. Instead of semiglobally or locally stabilizing, the resultant control policy is globally stabilizing for a general class of nonlinear polynomial systems. Furthermore, in the absence of the a priori knowledge of the system dynamics, an online learning method is devised to implement the proposed policy iteration technique by generalizing the current ADP theory. Finally, three numerical examples are provided to validate the effectiveness of the proposed method.

Posted in: Applications of reinforcement learning to control engineering , Tagged: ,

The quick-intuition vs. slow-deliberation dilemma from a decision-making perspective

December 22, 2015 17:36 ,

Y-Lan Boureau, Peter Sokol-Hessner, Nathaniel D. Daw, Deciding How To Decide: Self-Control and Meta-Decision Making, Trends in Cognitive Sciences, Volume 19, Issue 11, November 2015, Pages 700-710, ISSN 1364-6613, DOI: 10.1016/j.tics.2015.08.013.

Many different situations related to self control involve competition between two routes to decisions: default and frugal versus more resource-intensive. Examples include habits versus deliberative decisions, fatigue versus cognitive effort, and Pavlovian versus instrumental decision making. We propose that these situations are linked by a strikingly similar core dilemma, pitting the opportunity costs of monopolizing shared resources such as executive functions for some time, against the possibility of obtaining a better outcome. We offer a unifying normative perspective on this underlying rational meta-optimization, review how this may tie together recent advances in many separate areas, and connect several independent models. Finally, we suggest that the crucial mechanisms and meta-decision variables may be shared across domains.

Posted in: Cognitive sciences , Tagged: ,

A possible framework for the relationship between culture, behavior and the brain

December 22, 2015 17:33 ,

Shihui Han, Yina Ma, A Culture–Behavior–Brain Loop Model of Human Development, Trends in Cognitive Sciences, Volume 19, Issue 11, November 2015, Pages 666-676, ISSN 1364-6613, DOI: 10.1016/j.tics.2015.08.010.

Increasing evidence suggests that cultural influences on brain activity are associated with multiple cognitive and affective processes. These findings prompt an integrative framework to account for dynamic interactions between culture, behavior, and the brain. We put forward a culture–behavior–brain (CBB) loop model of human development that proposes that culture shapes the brain by contextualizing behavior, and the brain fits and modifies culture via behavioral influences. Genes provide a fundamental basis for, and interact with, the CBB loop at both individual and population levels. The CBB loop model advances our understanding of the dynamic relationships between culture, behavior, and the brain, which are crucial for human phylogeny and ontogeny. Future brain changes due to cultural influences are discussed based on the CBB loop model.

Posted in: Cognitive sciences , Tagged:

On how moral can shape perception

December 22, 2015 17:30 ,

Ana P. Gantman, Jay J. Van Bavel,Moral Perception, Trends in Cognitive Sciences, Volume 19, Issue 11, November 2015, Pages 631-633, ISSN 1364-6613, DOI: 10.1016/j.tics.2015.08.004.

Based on emerging research, we propose that human perception is preferentially attuned to moral content. We describe how moral concerns enhance detection of morally relevant stimuli, and both command and direct attention. These perceptual processes, in turn, have important consequences for moral judgment and behavior.

Posted in: Cognitive sciences , Tagged:

Scheduling of communications between several nodes for better achieving real-time constraints in a distributed control system, and also a very detailed dynamical model of a wheeled vehicle

November 12, 2015 20:08 ,

Naim Bajcinca, Wireless cars: A cyber-physical approach to vehicle dynamics control, Mechatronics, Volume 30, September 2015, Pages 261-274, ISSN 0957-4158, DOI: 10.1016/j.mechatronics.2015.04.016.

A non-conventional drive-by-wireless technology for guidance and control of a redundantly actuated electric car supported by an on-board wireless network of sensors, actuators and control units is proposed in this article. Several optimization-based distributed feedforward control schemes are developed for such powertrain infrastructures. In view of the limitations of the commercial off-the-shelf wireless communication technologies and the harshness of the in-vehicle environments, a pressing design and implementation aspect, in addition to the robustness against information loss, refers to fulfilling the hard real-time computational requirements. In this work, we address such problems by introducing several distributed event-based control schemes in conjunction with adaptive scheduling at the protocol level. Hereby we obtain a simple tuning mechanism to compromise between the outcome accuracy and computation efficiency (i.e., communication traffic intensity). Using simulative evaluations, we demonstrate the viability of the proposed algorithms and illustrate the impact of external interferences in an IEEE 802.15.4 based wireless communication solution.

Posted in: Communication networks, Task scheduling , Tagged: , ,

Study of how a complex motion planning problem solved through RRT can benefit from parallelization

November 12, 2015 19:59 ,

Brian W. Satzinger, Chelsea Lau, Marten Byl, Katie Byl, Tractable locomotion planning for RoboSimian, The International Journal of Robotics Research November 2015 vol. 34 no. 13 1541-1558, DOI: 10.1177/0278364915584947.

This paper investigates practical solutions for low-bandwidth, teleoperated mobility for RoboSimian in complex environments. Locomotion planning for this robot is challenging due to kinematic redundancy. We present an end-to-end planning method that exploits a reduced-dimension rapidly-exploring random tree search, constraining a subset of limbs to an inverse kinematics table. Then, we evaluate the performance of this approach through simulations in randomized environments and in the style of the Defense Advanced Research Projects Agency Robotics Challenges terrain both in simulation and with hardware.
We also illustrate the importance of allowing for significant body motion during swing leg motions on extreme terrain and quantify the trade-offs between computation time and execution time, subject to velocity and acceleration limits of the joints. These results lead us to hypothesize that appropriate statistical “investment” of parallel computing resources between competing formulations or flavors of random planning algorithms can improve motion planning performance significantly. Motivated by the need to improve the speed of limbed mobility for the Defense Advanced Research Projects Agency Robotics Challenge, we introduce one formulation of this resource allocation problem as a toy example and discuss advantages and implications of such trajectory planning for tractable locomotion on complex terrain.

Posted in: Robot motion planning , Tagged: ,