Abstract

3D LiDARs and 2D cameras are increasingly being used alongside each other in sensor rigs for perception tasks. Before these sensors can be used to gather meaningful data, however, their extrinsics (and intrinsics) need to be accurately calibrated, as the performance of the sensor rig is extremely sensitive to these calibration parameters. A vast majority of existing calibration techniques require significant amounts of data and/or calibration targets and human effort, severely impacting their applicability in large-scale production systems. We address this gap with CalibNet: a geometrically supervised deep network capable of automatically estimating the 6-DoF rigid body transformation between a 3D LiDAR and a 2D camera in real-time. CalibNet alleviates the need for calibration targets, thereby resulting in significant savings in calibration efforts. During training, the network only takes as input a LiDAR point cloud, the corresponding monocular image, and the camera calibration matrix K. At train time, we do not impose direct supervision (i.e., we do not directly regress to the calibration parameters, for example). Instead, we train the network to predict calibration parameters that maximize the geometric and photometric consistency of the input images and point clouds. CalibNet learns to iteratively solve the underlying geometric problem and accurately predicts extrinsic calibration parameters for a wide range of mis-calibrations, without requiring retraining or domain adaptation.

Abstract

In this paper, we present an efficient algorithm for solving a class of chance constrained optimization under non-parametric uncertainty. Our algorithm is built on the possibility of representing arbitrary distributions as functions in Reproducing Kernel Hilbert Space (RKHS). We use this foundation to formulate chance-constrained optimization as one of minimizing the distance between a desired distribution and the distribution of the constraint functions in the RKHS. We provide a systematic way of constructing the desired distribution based on a notion of scenario proximation. Furthermore, we use the kernel trick to show that the computational complexity of our reformulated optimization problem is comparable to solving a deterministic variant of the chance-constrained optimization. We validate our formulation on two important robotic/control applications: (i) reactive collision avoidance of mobile robots in uncertain dynamic environments and (ii) inverse dynamics based path tracking of manipulators under perception uncertainty. In both these applications, the underlying chance constraints are defined over highly non-linear and non-convex functions of the uncertain parameters and possibly also decision variables. We also benchmark our formulation with the existing approaches in terms of sample complexity and the achieved optimal cost highlighting significant improvements in both these metrics.

Abstract

Sparse Bayesian learning (SBL) has been used to obtain source direction-of-arrivals (DoAs) from uniform linear array (ULA) data. The maximum number of sources that can be resolved using a ULA is limited by the number of sensors in the array. It is known that sparse linear arrays such as co-prime and nested arrays can resolve more sources than the number of sensors. In this paper we demonstrate this using SBL. We compute the mean squared error in source power estimation as various parameters are varied.

Abstract

Convolutional Neural Networks (CNNs) are rapidly gaining popularity in varied fields. Due to their increasingly deep and computationally heavy structures, it is difficult to deploy them on energy constrained mobile applications. Hardware accelerators such as FPGAs have come up as an attractive alternative. However, with the limited on-chip memory and computation resources of FPGA, meeting the high memory throughput requirement and exploiting the parallelism of CNNs is a major challenge. We propose a high-performance FPGA based architecture - Depth Concatenation and Inter-Layer Fusion based ConvNet Accelerator - DeCoILFNet which exploits the intra-layer parallelism of CNNs by flattening across depth and combines it with a highly pipelined data flow across the layers enabling inter-layer fusion. This architecture significantly reduces off-chip memory accesses and maximizes the throughput. Compared to a 3.5GHz hexa-core Intel Xeon E7 caffe-implementation, our 120MHz FPGA accelerator is 30X faster. In addition, our design reduces external memory access by 11.5X along with a speedup of more than 2X in the number of clock cycles compared to state-of-the-art FPGA accelerators.

Abstract

We propose a novel Line based parameterization for category specific CAD models. The proposed parameterization associates 3D category-specific CAD model and object under consideration using a dictionary based RANSAC method that uses object Viewpoints as prior and edges detected in the respective intensity image of the scene. The association problem is posed as a classical Geometry problem rather than being dataset driven, thus saving the time and labour that one invests in annotating dataset to train Keypoint Network[1, 2] for different category objects. Besides eliminating the need of dataset preparation, the approach also speeds up the entire process as this method processes the image only once for all objects, thus eliminating the need of invoking the network for every object in an image across all images. A 3D-2D edge association module followed by a resection algorithm for lines is used to recover object poses. The formulation optimizes for shape and pose of the object, thus aiding in recovering object 3D structure more accurately. Finally, a Factor Graph formulation is used to combine object poses with camera odometry to formulate a SLAM problem.

Abstract

Using simulations and data, we localize a quiet source in the presence of an interferer. The SWellEx-96 Event S59 consists of a submerged source towed along an isobath over a 65 min duration with an interferer traversing the source track. This range independent, multi-frequency scenario includes mismatch, non-stationary noise, and operational uncertainty. Mismatch is defined as a misalignment between the actual source field observed at the array and the modeled replica vector. The noise process changes likely with time. This is modelled as a heteroscedastic Gaussian process, meaning that the noise variance is non-stationary across snapshots. Sparse Bayesian learning (SBL) has been applied previously to the matched field processing application [Gemba et al, J. Acoust. Soc. Am., 141:3411-3420, 2017]. Results demonstrate that SBL exhibits desirable robustness properties and improved localization …

Abstract

Mitigation of loopback self-interference (LSI) is one of the main challenges in full-duplex (FD) wireless communication systems. In this letter, we present the design of optimal transceiver and relay processing algorithms for an FD two-way amplify-and-forward (AF) multiple-input multiple-output relaying system. We consider a realistic scenario where the available channel state information of the LSI channels is imperfect. The resultant residual LSI is suppressed by the suitable design of precoders and receive filters. All the precoders and receive filters are updated in each time slot in order to combat the cumulative interference effect caused by AF operation of the FD relay. We derive a simple recursive equation to keep track of this cumulative interference. The performance of the proposed design is demonstrated via the simulation results.

Abstract

In this paper, we present the optimal power allocation and relay precoder design for a cognitive relay network employing non-orthogonal multiple access (NOMA) technique. The secondary user (SU) nodes share the spectrum with the licensed primary user (PU) while keeping the interference at PU nodes below a permissible threshold. The cognitive nodes communicate with each other with the assistance of a cognitive amplify and forward (AF) relay equipped with multiple antennas. The proposed source power allocation and relay precoder design aim at maximizing the sum-rate of the cognitive destination nodes while maintaining the interference to the PU node below the specified threshold. Given that the SU transmit node has to restrict its transmit power in order to reduce the interference to the PU, use of NOMA can significantly improve the SU performance. The resulting optimization problem is non-convex in its original form. In order to circumvent the difficulties associated with the non-convexity, we employ minorization-maximization technique to obtain convex approximations to some of the non- convex functions appearing in the problem. We then solve this problem to obtain the optimal resource allocation policy at source and precoder design at the relay. Numerical results are provided to illustrate the performance of the proposed design for various operating conditions and parameters.

Abstract

Millimeter-wave (mmWave) communication is a promising technology for future wireless systems due to the availability of huge unlicensed bandwidth. However, the need for large number of radio frequency (RF) chains associated with the antenna array and the corresponding increase in hardware complexity and power consumption are major stumbling blocks to its implementability. In this paper, we propose a low-complexity in-band full-duplex relay-assisted mmWave communication system design. We obtain the proposed multiple-input multiple-output analog–digital hybrid transceivers and relay filters by minimizing the overall sum-mean-square-error while mitigating the effect of residual loopback self-interference (LSI) in the system. The number of RF chains required in the proposed design is less than the number of antennas. We first present a design assuming the availability of perfect channel state information (CSI) at all the nodes. Later, we extend it to a robust design assuming a more realistic scenario, where the available CSI is imperfect. Furthermore, the LSI channel knowledge is assumed to be imperfect for both the designs rendering them robust to errors in loopback CSI. We employ sparse approximation technique to reduce the hardware complexity in the proposed system designs. The proposed algorithms are shown to converge to a limit even though the global convergence is hard to prove since the overall problem is non-convex. The hardware complexity-performance tradeoff of the proposed design is analyzed. Furthermore, the resilience of the robust design in the presence of CSI errors and the performance of both the proposed designs over various parameters are illustrated via numerical simulations.

Abstract

High arousal speech is produced by speakers when they raise their loudness levels. There are deviations from neutral speech, especially in the excitation component of the speech production mechanism in the high arousal mode. In this study, a parameter, called the time-frequency spectral error (TF e) is derived using the single frequency filtering (SFF) spectrogram. It is used to characterize the high arousal regions in speech signals. The proposed parameter captures the fine temporal and spectral variations due to changes in the excitation source.