Self-selected walking speed is a key outcome for exercise-based rehabilitation programs following lower-extremity trauma. This work introduces a novel reinforcement learning-based assist-as-needed (RL-AAN) controller for ankle exoskeletons, aimed at gait speed training. Built on an actor–critic architecture, the RL-AAN controller integrates a control objective that balances the trade-off between expected stride velocity (SV) errors and exoskeleton assistance. This approach allows the exoskeleton to progressively reduce ankle plantar- and dorsiflexion (PDF) assistance as the user’s performance improves, promoting active participation. The desired assistive torque is computed as the product of the actor output and the wearer’s biomechanical ankle PDF moment, estimated by a subject-agnostic model, thereby ensuring personalized and biomechanically relevant assistance. In a proof-of-concept study with healthy individuals walking on a self-paced treadmill with ankle weights, the RL-AAN controller outperformed a conventional Fixed-K controller—achieving greater immediate speed increases during assisted walking (14.2% vs. 10.0% relative to unassisted perturbed walking) and inducing short-term gait speed adaptation post-training, not observed with the conventional controller. These findings highlight the potential of RL-AAN control for subject-tailored gait training, with promising clinical implications for exercise-based rehabilitation in individuals with neurological or musculoskeletal gait impairments.

System design tools are often only available as input–output blackboxes: for a given design as input, they compute an output representing system behavior. Blackboxes are intended to be run in the forward direction. This article presents a new method of solving the “inverse design problem,” namely, given requirements or constraints on output, find an input that also optimizes an objective function. This problem is challenging for several reasons. First, blackboxes are not designed to be run in reverse. Second, inputs and outputs can be discrete and continuous. Third, finding designs concurrently satisfying a set of requirements is hard because designs satisfying individual requirements may conflict with each other. Fourth, blackbox evaluations can be expensive. Finally, evaluations can sometimes fail to produce an output due to nonconvergence of underlying numerical algorithms. This article presents CNMA, a new method of solving the inverse problem that overcomes these challenges. CNMA tries to sample only the part of the design space relevant to solving the inverse problem, leveraging the power of neural networks, mixed-integer linear programs, and a new learning-from-failure feedback loop. This article also presents a parallel version of CNMA that improves the efficiency and quality of solutions over the sequential version and tries to steer it away from local optima. CNMA’s performance is evaluated against conventional optimization methods for seven nonlinear design problems of 8 (two problems), 10, 15, 36 and 60 real-valued dimensions and one with 186 binary dimensions. Conventional methods evaluated are stable, off-the-shelf implementations of the Bayesian optimization with the Gaussian Processes, Nelder–Mead, and Random Search. The first two do not even produce a solution for problems that are high dimensional, having both discrete and continuous variables or whose blackboxes fail to return values for some inputs. CNMA produces solutions for all problems. When conventional methods do produce solutions, CNMA improves upon their performance by 1%–87%.

Light Detection and Ranging (LIDAR) scans are increasingly being used for 3D map construction and reverse engineering. The utility and benefit of the processed data maybe enhanced if the objects and geometry of the area scanned can be segmented and labeled. In this paper, we present techniques to model the intensity of the laser reflection return from a point during LIDAR scanning to determine diffuse and specular reflection properties of the scanned surface. Using several illumination models, the reflection properties of the surface are characterized by Lambertian diffuse reflection model and Blinn-Phong, Gaussian and Beckmann specular models. Experimental set up with eight different surfaces with varied textures and glossiness enabled measurement of algorithm performance. Examples of point cloud segmentation with the presented approach are presented.

This paper presents methodologies to accelerate the registration of 3D point cloud segments by using hue data from the associated imagery. The proposed variant of the Iterative Closest Point (ICP) algorithm combines both normalized point range data and weighted hue value calculated from RGB data of an image registered 3D point cloud. A k-d tree based nearest neighbor search is used to associated common points in {x, y, z, hue} 4D space. The unknown rigid translation and rotation matrix required for registration is iteratively solved using Singular Value Decomposition (SVD) method. A mobile robot mounted scanner was used to generate color point cloud segments over a large area. The 4D ICP registration has been compared with typical 3D ICP and numerical results on the generated map segments shows that the 4D method resolves ambiguity in registration and converges faster than the 3D ICP.