More Like this

1. Bearing-Only Localization of a Quasi-Static Sound Source With a Binaural Microphone Array

   https://doi.org/10.1115/DSCC2020-3235  

   Bradley, Aidan J.; Shirazi, Masoud J.; Abaid, Nicole (October 2020, ASME Dynamic Systems and Control Conference)

   null (Ed.)

   Abstract Sound source localization is the ability to successfully understand the bearing and distance of a sound in space. The challenge of sound source localization has been a major are of research for engineers, especially those studying robotics, for decades. One of the main topics of focus is the ability for robots to track objects, human voices, or other robots robustly and accurately. Common ways to accomplish this goal may use large arrays, computationally intensive machine learning methods, or known dynamic models of a system which may not always be available. We seek to simplify this problem using a minimal amount of inexpensive equipment alongside a Bayesian estimator, capable of localizing an emitter using easily available a-priori information and timing data received from a prototype binaural sensor. We perform an experiment in a full anechoic chamber with a sound source moving at a constant speed; this experimental environment provides a space that allows us to isolate the performance of the sensor. We find that, while our current system isn’t perfect, it is able to track the general motion of a sound source and the path to even more accurate tracking in the future is clear. 

   more » « less
2. Learning To Maximize Welfare with a Reusable Resource

   https://doi.org/10.1145/3530893  

   Faw, Matthew; Papadigenopoulos, Orestis; Caramanis, Constantine; Shakkottai, Sanjay (May 2022, Proceedings of the ACM on Measurement and Analysis of Computing Systems)

   Considerable work has focused on optimal stopping problems where random IID offers arrive sequentially for a single available resource which is controlled by the decision-maker. After viewing the realization of the offer, the decision-maker irrevocably rejects it, or accepts it, collecting the reward and ending the game. We consider an important extension of this model to a dynamic setting where the resource is "renewable'' (a rental, a work assignment, or a temporary position) and can be allocated again after a delay period d. In the case where the reward distribution is known a priori, we design an (asymptotically optimal) 1/2-competitive Prophet Inequality, namely, a policy that collects in expectation at least half of the expected reward collected by a prophet who a priori knows all the realizations. This policy has a particularly simple characterization as a thresholding rule which depends on the reward distribution and the blocking period d, and arises naturally from an LP-relaxation of the prophet's optimal solution. Moreover, it gives the key for extending to the case of unknown distributions; here, we construct a dynamic threshold rule using the reward samples collected when the resource is not blocked. We provide a regret guarantee for our algorithm against the best policy in hindsight, and prove a complementing minimax lower bound on the best achievable regret, establishing that our policy achieves, up to poly-logarithmic factors, the best possible regret in this setting. 

   more » « less
3. Information conveyed by voice quality

   https://doi.org/10.1121/10.0024609  

   Kreiman, Jody (February 2024, The Journal of the Acoustical Society of America)

   The problem of characterizing voice quality has long caused debate and frustration. The richness of the available descriptive vocabulary is overwhelming, but the density and complexity of the information voices convey lead some to conclude that language can never adequately specify what we hear. Others argue that terminology lacks an empirical basis, so that language-based scales are inadequate a priori. Efforts to provide meaningful instrumental characterizations have also had limited success. Such measures may capture sound patterns but cannot at present explain what characteristics, intentions, or identity listeners attribute to the speaker based on those patterns. However, some terms continually reappear across studies. These terms align with acoustic dimensions accounting for variance across speakers and languages and correlate with size and arousal across species. This suggests that labels for quality rest on a bedrock of biology: We have evolved to perceive voices in terms of size/arousal, and these factors structure both voice acoustics and descriptive language. Such linkages could help integrate studies of signals and their meaning, producing a truly interdisciplinary approach to the study of voice. 

   more » « less
4. Obtaining Information Leakage Bounds via Approximate Model Counting

   https://doi.org/10.1145/3591281  

   Saha, Seemanta; Ghentiyala, Surendra; Lu, Shihua; Bang, Lucas; Bultan, Tevfik (June 2023, Proceedings of the ACM on Programming Languages)

   Information leaks are a significant problem in modern software systems. In recent years, information theoretic concepts, such as Shannon entropy, have been applied to quantifying information leaks in programs. One recent approach is to use symbolic execution together with model counting constraints solvers in order to quantify information leakage. There are at least two reasons for unsoundness in quantifying information leakage using this approach: 1) Symbolic execution may not be able to explore all execution paths, 2) Model counting constraints solvers may not be able to provide an exact count. We present a sound symbolic quantitative information flow analysis that bounds the information leakage both for the cases where the program behavior is not fully explored and the model counting constraint solver is unable to provide a precise model count but provides an upper and a lower bound. We implemented our approach as an extension to KLEE for computing sound bounds for information leakage in C programs. 

   more » « less
5. Task-Guided Inverse Reinforcement Learning under Partial Information

   https://doi.org/10.1609/icaps.v32i1.19785  

   Djeumou, Franck; Cubuktepe, Murat; Lennon, Craig; Topcu, Ufuk (June 2022, Proceedings of the International Conference on Automated Planning and Scheduling)

   We study the problem of inverse reinforcement learning (IRL), where the learning agent recovers a reward function using expert demonstrations. Most of the existing IRL techniques make the often unrealistic assumption that the agent has access to full information about the environment. We remove this assumption by developing an algorithm for IRL in partially observable Markov decision processes (POMDPs). The algorithm addresses several limitations of existing techniques that do not take the information asymmetry between the expert and the learner into account. First, it adopts causal entropy as the measure of the likelihood of the expert demonstrations as opposed to entropy in most existing IRL techniques, and avoids a common source of algorithmic complexity. Second, it incorporates task specifications expressed in temporal logic into IRL. Such specifications may be interpreted as side information available to the learner a priori in addition to the demonstrations and may reduce the information asymmetry. Nevertheless, the resulting formulation is still nonconvex due to the intrinsic nonconvexity of the so-called forward problem, i.e., computing an optimal policy given a reward function, in POMDPs. We address this nonconvexity through sequential convex programming and introduce several extensions to solve the forward problem in a scalable manner.This scalability allows computing policies that incorporate memory at the expense of added computational cost yet also outperform memoryless policies. We demonstrate that, even with severely limited data, the algorithm learns reward functions and policies that satisfy the task and induce a similar behavior to the expert by leveraging the side information and incorporating memory into the policy. 

   more » « less