Multi-agent collision-free trajectory planning and control subject to different goal requirements and system dynamics has been extensively studied, and is gaining recent attention in the realm of machine and reinforcement learning. However, in partic
ular when using a large number of agents, constructing a least-restrictive collision avoidance policy is of utmost importance for both classical and learning-based methods. In this paper, we propose a Least-Restrictive Collision Avoidance Module (LR-CAM) that evaluates the safety of multi-agent systems and takes over control only when needed to prevent collisions. The LR-CAM is a single policy that can be wrapped around policies of all agents in a multi-agent system. It allows each agent to pursue any objective as long as it is safe to do so. The benefit of the proposed least-restrictive policy is to only interrupt and overrule the default controller in case of an upcoming inevitable danger. We use a Long Short-Term Memory (LSTM) based Variational Auto-Encoder (VAE) to enable the LR-CAM to account for a varying number of agents in the environment. Moreover, we propose an off-policy meta-reinforcement learning framework with a novel reward function based on a Hamilton-Jacobi value function to train the LR-CAM. The proposed method is fully meta-trained through a ROS based simulation and tested on real multi-agent system. Our results show that LR-CAM outperforms the classical least-restrictive baseline by 30 percent. In addition, we show that even if a subset of agents in a multi-agent system use LR-CAM, the success rate of all agents will increase significantly.
Query rewriting (QR) systems are widely used to reduce the friction caused by errors in a spoken language understanding pipeline. However, the underlying supervised models require a large number of labeled pairs, and these pairs are hard and costly t
o be collected. Therefore, We propose an augmentation framework that learns patterns from existing training pairs and generates rewrite candidates from rewrite labels inversely to compensate for insufficient QR training data. The proposed framework casts the augmentation problem as a sequence-to-sequence generation task and enforces the optimization process with a policy gradient technique for controllable rewarding. This approach goes beyond the traditional heuristics or rule-based augmentation methods and is not constrained to generate predefined patterns of swapping/replacing words. Our experimental results show its effectiveness compared with a fully trained QR baseline and demonstrate its potential application in boosting the QR performance on low-resource domains or locales.
We propose a novel method for hierarchical entity classification that embraces ontological structure at both training and during prediction. At training, our novel multi-level learning-to-rank loss compares positive types against negative siblings ac
cording to the type tree. During prediction, we define a coarse-to-fine decoder that restricts viable candidates at each level of the ontology based on already predicted parent type(s). We achieve state-of-the-art across multiple datasets, particularly with respect to strict accuracy.
We ask whether text understanding has progressed to where we may extract event information through incremental refinement of bleached statements derived from annotation manuals. Such a capability would allow for the trivial construction and extension
of an extraction framework by intended end-users through declarations such as, Some person was born in some location at some time. We introduce an example of a model that employs such statements, with experiments illustrating we can extract events under closed ontologies and generalize to unseen event types simply by reading new definitions.
Multi-view learning improves the learning performance by utilizing multi-view data: data collected from multiple sources, or feature sets extracted from the same data source. This approach is suitable for primate brain state decoding using cortical n
eural signals. This is because the complementary components of simultaneously recorded neural signals, local field potentials (LFPs) and action potentials (spikes), can be treated as two views. In this paper, we extended broad learning system (BLS), a recently proposed wide neural network architecture, from single-view learning to multi-view learning, and validated its performance in decoding monkeys oculomotor decision from medial frontal LFPs and spikes. We demonstrated that medial frontal LFPs and spikes in non-human primate do contain complementary information about the oculomotor decision, and that the proposed multi-view BLS is a more effective approach for decoding the oculomotor decision than several classical and state-of-the-art single-view and multi-view learning approaches.
Sensing local environment through the motional response of small molecules lays the foundation of many fundamental technologies. The information of local viscosity, for example, is contained in the random rotational Brownian motions of molecules. How
ever, detection of the motions is challenging for molecules with sub-nanometer scale or high motional rates. Here we propose and experimentally demonstrate a novel method of detecting fast rotational Brownian motions of small magnetic molecules. With electronic spins as sensors, we are able to detect changes in motional rates, which yield different noise spectra and therefore different relaxation signals of the sensors. As a proof-of-principle demonstration, we experimentally implemented this method to detect the motions of gadolinium (Gd) complex molecules with nitrogen-vacancy (NV) centers in nanodiamonds. With all-optical measurements of the NV centers longitudinal relaxation, we distinguished binary solutions with varying viscosities. Our method paves a new way for detecting fast motions of sub-nanometer sized magnetic molecules with better spatial resolution than conventional optical methods. It also provides a new tool in designing better contrast agents in magnetic resonance imaging.
