Reinforcement Learning With Function Approximation for Traffic Signal Control

We propose, for the first time, a reinforcement learning (RL) algorithm with function approximation for traffic signal control. Our algorithm incorporates state-action features and is easily implementable in high-dimensional settings. Prior work, e. g., the work of Abdulhai et al., on the application of RL to traffic signal control requires full-state representations and cannot be implemented, even in moderate-sized road networks, because the computational complexity exponentially grows in the numbers of lanes and junctions. We tackle this problem of the curse of dimensionality by effectively using feature-based state representations that use a broad characterization of the level of congestion as low, medium, or high. One advantage of our algorithm is that, unlike prior work based on RL, it does not require precise information on queue lengths and elapsed times at each lane but instead works with the aforementioned described features. The number of features that our algorithm requires is linear to the number of signaled lanes, thereby leading to several orders of magnitude reduction in the computational complexity. We perform implementations of our algorithm on various settings and show performance comparisons with other algorithms in the literature, including the works of Abdulhai et al. and Cools et al., as well as the fixed-timing and the longest queue algorithms. For comparison, we also develop an RL algorithm that uses full-state representation and incorporates prioritization of traffic, unlike the work of Abdulhai et al. We observe that our algorithm outperforms all the other algorithms on all the road network settings that we consider.

Contrained linear spectral unmixing technique for regional land cover mapping using MODIS data

Over the last few decades, there has been a significant land cover (LC) change across the globe due to the increasing demand of the burgeoning population and urban sprawl. In order to take account of the change, there is a need for accurate and up- to-date LC maps. Mapping and monitoring of LC in India is being carried out at national level using multi-temporal IRS AWiFS data. Multispectral data such as IKONOS, Landsat- TM/ETM+, IRS-1C/D LISS-III/IV, AWiFS and SPOT-5, etc. have adequate spatial resolution (~ 1m to 56m) for LC mapping to generate 1:50,000 maps. However, for developing countries and those with large geographical extent, seasonal LC mapping is prohibitive with data from commercial sensors of limited spatial coverage. Superspectral data from the MODIS sensor are freely available, have better temporal (8 day composites) and spectral information. MODIS pixels typically contain a mixture of various LC types (due to coarse spatial resolution of 250, 500 and 1000 m), especially in more fragmented landscapes. In this context, linear spectral unmixing would be useful for mapping patchy land covers, such as those that characterise much of the Indian subcontinent. This work evaluates the existing unmixing technique for LC mapping using MODIS data, using end- members that are extracted through Pixel Purity Index (PPI), Scatter plot and N-dimensional visualisation. The abundance maps were generated for agriculture, built up, forest, plantations, waste land/others and water bodies. The assessment of the results using ground truth and a LISS-III classified map shows 86% overall accuracy, suggesting the potential for broad-scale applicability of the technique with superspectral data for natural resource planning and inventory applications.

Reinforcement learning with average cost for adaptive control of traffic lights at intersections

We propose for the first time two reinforcement learning algorithms with function approximation for average cost adaptive control of traffic lights. One of these algorithms is a version of Q-learning with function approximation while the other is a policy gradient actor-critic algorithm that incorporates multi-timescale stochastic approximation. We show performance comparisons on various network settings of these algorithms with a range of fixed timing algorithms, as well as a Q-learning algorithm with full state representation that we also implement. We observe that whereas (as expected) on a two-junction corridor, the full state representation algorithm shows the best results, this algorithm is not implementable on larger road networks. The algorithm PG-AC-TLC that we propose is seen to show the best overall performance.

Network pricing for QoS: A 'Regulation' approach

V. S. Borkar’s work was supported in part by grant number III.5(157)/99-ET from the Department of Science and Technology, Government of India. D. Manjunath’s work was supported in part by grant number 1(1)/2004-E-Infra from the Ministry of Information Technology, Government of India.

Design and Evaluation of a Robust Optical Beam-Interruption-Based Vehicle Classifier System

This paper presents the design and development of a novel optical vehicle classifier system, which is based on interruption of laser beams, that is suitable for use in places with poor transportation infrastructure. The system can estimate the speed, axle count, wheelbase, tire diameter, and the lane of motion of a vehicle. The design of the system eliminates the need for careful optical alignment, whereas the proposed estimation strategies render the estimates insensitive to angular mounting errors and to unevenness of the road. Strategies to estimate vehicular parameters are described along with the optimization of the geometry of the system to minimize estimation errors due to quantization. The system is subsequently fabricated, and the proposed features of the system are experimentally demonstrated. The relative errors in the estimation of velocity and tire diameter are shown to be within 0.5% and to change by less than 17% for angular mounting errors up to 30 degrees. In the field, the classifier demonstrates accuracy better than 97.5% and 94%, respectively, in the estimation of the wheelbase and lane of motion and can classify vehicles with an average accuracy of over 89.5%.

Rollover-Preventive Force Synthesis at Active Suspensions in a Vehicle Performing a Severe Maneuver With Wheels Lifted Off

Among the intelligent safety technologies for road vehicles, active suspensions controlled by embedded computing elements for preventing rollover have received a lot of attention. The existing models for synthesizing and allocating forces in such suspensions are conservatively based on the constraints that are valid until no wheels lift off the ground. However, the fault tolerance of the rollover-preventive systems can be enhanced if the smart/active suspensions can intervene in the more severe situation in which the wheels have just lifted off the ground. The difficulty in computing control in the last situation is that the vehicle dynamics then passes into the regime that yields a model involving disjunctive constraints on the dynamics. Simulation of dynamics with disjunctive constraints in this context becomes necessary to estimate, synthesize, and allocate the intended hardware realizable forces in an active suspension. In this paper, we give an algorithm for the previously mentioned problem by solving it as a disjunctive dynamic optimization problem. Based on this, we synthesize and allocate the roll-stabilizing time-dependent active suspension forces in terms of sensor output data. We show that the forces obtained from disjunctive dynamics are comparable with existing force allocations and, hence, are possibly realizable in the existing hardware framework toward enhancing the safety and fault tolerance.

Hardware Accelerator for 3D Method of Moments based Parasitic Extraction

A Field Programmable Gate Array (FPGA) based hardware accelerator for multi-conductor parasitic capacitance extraction, using Method of Moments (MoM), is presented in this paper. Due to the prohibitive cost of solving a dense algebraic system formed by MoM, linear complexity fast solver algorithms have been developed in the past to expedite the matrix-vector product computation in a Krylov sub-space based iterative solver framework. However, as the number of conductors in a system increases leading to a corresponding increase in the number of right-hand-side (RHS) vectors, the computational cost for multiple matrix-vector products present a time bottleneck, especially for ill-conditioned system matrices. In this work, an FPGA based hardware implementation is proposed to parallelize the iterative matrix solution for multiple RHS vectors in a low-rank compression based fast solver scheme. The method is applied to accelerate electrostatic parasitic capacitance extraction of multiple conductors in a Ball Grid Array (BGA) package. Speed-ups up to 13x over equivalent software implementation on an Intel Core i5 processor for dense matrix-vector products and 12x for QR compressed matrix-vector products is achieved using a Virtex-6 XC6VLX240T FPGA on Xilinx's ML605 board.

Multi-agent Reinforcement Learning for Traffic Signal Control

Optimal control of traffic lights at junctions or traffic signal control (TSC) is essential for reducing the average delay experienced by the road users amidst the rapid increase in the usage of vehicles. In this paper, we formulate the TSC problem as a discounted cost Markov decision process (MDP) and apply multi-agent reinforcement learning (MARL) algorithms to obtain dynamic TSC policies. We model each traffic signal junction as an independent agent. An agent decides the signal duration of its phases in a round-robin (RR) manner using multi-agent Q-learning with either is an element of-greedy or UCB 3] based exploration strategies. It updates its Q-factors based on the cost feedback signal received from its neighbouring agents. This feedback signal can be easily constructed and is shown to be effective in minimizing the average delay of the vehicles in the network. We show through simulations over VISSIM that our algorithms perform significantly better than both the standard fixed signal timing (FST) algorithm and the saturation balancing (SAT) algorithm 15] over two real road networks.

A systems approach to rural housing

An attempt is made in this paper to arrive at a methodology for generating building technologies appropriate to rural housing. An evaluation of traditional modern' technologies currently in use reveals the need for alternatives. The lacunae in the presently available technologies also lead to a definition of rural housing needs. It is emphasised that contending technologies must establish a 'goodness of fit' between the house form and the pattern of needs. A systems viewpoint which looks at the dynamic process of building construction and the static structure of the building is then suggested as a means to match the technologies to the needs. The process viewpoint emphasises the role of building materials production and transportation in achieving desired building performances. A couple of examples of technological alternatives like the compacted soil block and the polythene-stabilised soil roof covering are then discussed. The static structural system viewpoint is then studied to arrive at methodologies of cost reduction. An illustrative analysis is carried out using the dynamic programming technique, to arrive at combinations of alternatives for the building components which lead to cost reduction. Some of the technological options are then evaluated against the need patterns. Finally, a guideline for developments in building technology is suggested