This work studies online learningbased trajectory planning for multiple autonomous underwater vehicles (AUVs) to estimate a water parameter field of interest in the underice environment. A centralized system is considered, where several fixed access points on the ice layer are introduced as gateways for communications between the AUVs and a remote data fusion center. We model the water parameter field of interest as a Gaussian process with unknown hyperparameters. The AUV trajectories for sampling are determined on an epochbyepoch basis. At the end of each epoch, the access points relay the observed field samples from all the AUVs to the fusion center, which computes the posterior distribution of the field based on the Gaussian process regression and estimates the field hyperparameters. The optimal trajectories of all the AUVs in the next epoch are determined to maximize a longterm reward that is defined based on the field uncertainty reduction and the AUV mobility cost, subject to the kinematics constraint, the communication constraint and the sensing area constraint. We formulate the adaptive trajectory planning problem as a Markov decision process (MDP). A reinforcement learningbased online learning algorithm is designed to determine the optimal AUV trajectories in a constrained continuous space. Simulation resultsmore »
Energybased continuous inverse optimal control.
The problem of continuous inverse optimal control (over finite time horizon) is to learn the unknown cost function over the sequence of continuous control variables from expert demonstrations. In this article, we study this fundamental problem in the framework of energybased model, where the observed expert trajectories are assumed to be random samples from a probability density function defined as the exponential of the negative cost function up to a normalizing constant. The parameters of the cost function are learned by maximum likelihood via an “analysis by synthesis” scheme, which iterates (1) synthesis step: sample the synthesized trajectories from the current probability density using the Langevin dynamics via backpropagation through time, and (2) analysis step: update the model parameters based on the statistical difference between the synthesized trajectories and the observed trajectories. Given the fact that an efficient optimization algorithm is usually available for an optimal control problem, we also consider a convenient approximation of the above learning method, where we replace the sampling in the synthesis step by optimization. Moreover, to make the sampling or optimization more efficient, we propose to train the energybased model simultaneously with a topdown trajectory generator via cooperative learning, where the trajectory generator is more »
 Award ID(s):
 2015577
 Publication Date:
 NSFPAR ID:
 10351397
 Journal Name:
 IEEE transactions on neural networks and learning systems
 ISSN:
 2162237X
 Sponsoring Org:
 National Science Foundation
More Like this


Abstract
<p>This data set for the manuscript entitled "Design of Peptides that Fold and SelfAssemble on Graphite" includes all files needed to run and analyze the simulations described in the this manuscript in the molecular dynamics software NAMD, as well as the output of the simulations. The files are organized into directories corresponding to the figures of the main text and supporting information. They include molecular model structure files (NAMD psf or Amber prmtop format), force field parameter files (in CHARMM format), initial atomic coordinates (pdb format), NAMD configuration files, Colvars configuration files, NAMD log files, and NAMD output including restart files (in binary NAMD format) and trajectories in dcd format (downsampled to 10 ns per frame). Analysis is controlled by shell scripts (Bashcompatible) that call VMD Tcl scripts or python scripts. These scripts and their output are also included.</p> <p>Version: 2.0</p> <p>Changes versus version 1.0 are the addition of the free energy of folding, adsorption, and pairing calculations (Sim_Figure7) and shifting of the figure numbers to accommodate this addition.</p> <p><br /> Conventions Used in These Files<br /> ===============================</p> <p>Structure Files<br /> <br />  graph_*.psf or sol_*.psf (original NAMD (XPLOR?) format psf file including atom details (type, charge, mass), 
Human trajectory prediction is critical for autonomous platforms like selfdriving cars or social robots. We present a latent belief energybased model (LBEBM) for diverse human trajectory forecast. LBEBM is a probabilistic model with cost function defined in the latent space to account for the movement history and social context. The low dimensionality of the latent space and the high expressivity of the EBM make it easy for the model to capture the multimodality of pedestrian trajectory distributions. LBEBM is learned from expert demonstrations (i.e., human trajectories) projected into the latent space. Sampling from or optimizing the learned LBEBM yields a belief vector which is used to make a path plan, which then in turn helps to predict a longrange trajectory. The effectiveness of LBEBM and the twostep approach are supported by strong empirical results. Our model is able to make accurate, multimodal, and social compliant trajectory predictions and improves over prior stateofthearts performance on the Stanford Drone trajectory prediction benchmark by 10:9% and on the ETHUCY benchmark by 27:6%.

Trajectory optimization o↵ers mature tools for motion planning in highdimensional spaces under dynamic constraints. However, when facing complex configuration spaces, cluttered with obstacles, roboticists typically fall back to samplingbased planners that struggle in very high dimensions and with continuous di↵erential constraints. Indeed, obstacles are the source of many textbook examples of problematic nonconvexities in the trajectoryoptimization prob lem. Here we show that convex optimization can, in fact, be used to reliably plan trajectories around obstacles. Specifically, we consider planning problems with collisionavoidance constraints, as well as cost penalties and hard constraints on the shape, the duration, and the velocity of the trajectory. Combining the properties of B ́ezier curves with a recentlyproposed framework for finding shortest paths in Graphs of Convex Sets (GCS), we formulate the planning problem as a compact mixedinteger optimization. In stark contrast with existing mixedinteger planners, the convex relaxation of our programs is very tight, and a cheap round ing of its solution is typically sufficient to design globallyoptimal trajectories. This reduces the mixedinteger program back to a simple convex optimization, and automatically provides optimality bounds for the planned trajectories. We name the proposed planner GCS, after its underlying optimization framework. We demonstrate GCS in simulationmore »

In this thesis we propose novel estimation techniques for localization and planning problems, which are key challenges in longterm autonomy. We take inspiration in our methods from nonparametric estimation and use tools such as kernel density estimation, nonlinear leastsquares optimization, binary masking, and random sampling. We show that these methods, by avoiding explicit parametric models, outperform existing methods that use them. Despite the seeming differences between localization and planning, we demonstrate in this thesis that the problems share core structural similarities. When real or simulationsampled measurements are expensive, noisy, or high variance, nonparametric estimation techniques give higherquality results in less time. We first address two localization problems. In order to permit localization with a set of ad hocplaced radios, we propose an ultrawideband (UWB) graph realization system to localize the radios. Our system achieves high accuracy and robustness by using kernel density estimation for measurement probability densities, by explicitly modeling antenna delays, and by optimizing this combination with a nonlinear least squares formulation. Next, in order to then support robotic navigation, we present a flexible system for simultaneous localization and mapping (SLAM) that combines elements from both traditional dense metric SLAM and topological SLAM, using a binary "masking function" tomore »