The success of the model predictive path integral control (MPPI) approach depends on the appropriate selection of the input distribution used for sampling. However, it can be challenging to select inputs that satisfy output constraints in dynamic environments. The main contribution of this paper is to propose an output-sampling-based MPPI (o-MPPI), which improves the ability of samples to satisfy output constraints and thereby increases MPPI efficiency. Comparative simulations and experiments of dynamic autonomous driving of bots around a track are provided to show that the proposed o-MPPI is more efficient and requires substantially (20-times) less number of rollouts and (4-times) smaller prediction horizon when compared with the standard MPPI for similar success rates.

Recent works have investigated bio-inspired strategies to transport objects using decentralized robot networks that only use local measurements without the need for communication between robots. Typically, there is an inverse relationship between the object deformation and the transport time, i.e., reducing the object deformation requires an increase in the transport time needed for transitioning from the initial configuration to the final configuration of the object. In contrast, the main contribution in this article is the development of a delayed self-reinforcement (DSR) approach that seeks to decentralize the ideal centralized transport that has no object deformation, and thereby, reduces the object deformation without increasing the transport time for the same specified transport trajectory. In the DSR method, each robot only uses already available prior-information to reinforce each robot's actions, and thus, the DSR implementation does not require additional information or changes in the network structure. Another contribution in this article is to analyze the potentially time-varying dynamics to establish conditions on the control parameters for stability and quantify the performance of the proposed DSR-based transport. Furthermore, experimental results are presented to show that the proposed cohesive transport method can reduce the deformation by at least 72% for the same transport time, when compared with the case without DSR.

This paper proposes an approach to make constant-spacing vehicle platoons robust to large delays and loss of communication. It is well known that centralized communication of the desired trajectory is important to simultaneously guarantee both string stability and constant-spacing in platoons. However, the performance of the resulting connected vehicle system (CVS) is vulnerable to large communication delays and communication loss. The main contribution of this work is a new delayed-self-reinforcement-based (DSR-based) approach that approximates the centralized communication based control by a decentralized predecessor follower (PF) control. The resulting blending of centralized communication with the decentralized DSR approach results in predecessor-leader follower (PLF) control with (i) robustness of the convergence to consensus under large communication delays and (ii) substantially-smaller spacing errors under loss of communication. Comparative simulations show that, for the same level of robustness to internal-stability and string-stability, the variation in settling time to consensus for PLF with DSR under large communication delays is 95% less than PLF without DSR and the steady-state error with DSR under loss of communication is 80% less than PLF without DSR.

This article studies imitation learning policies that encode task compliance to provide teleoperation assistance for remote manufacturing. The central challenge is how to handle off-nominal situations, such as out-of-sequence work or unplanned obstacles, since the assistance has not been trained to handle such scenarios. In such cases, there is potential for the assistance to degrade-rather than improve-operator performance. This work proposes a method that exploits the learned task compliance to classify persistent human actions as off-nominal, and attenuate assistance in these regions. Applied to a hole-cleaning task with n = 11 subjects, the proposed method shows up to 17% reduction in task completion time and up to 68% reduction in forces in off-nominal situations as compared to assistance without the method. Additionally, the method retains the performance improvements of assistance in nominal operating regimes.

Learning motion primitives from demonstration requires the human demonstrator to effectively relay the task intent to the robot controller. When the task intent is not reflected sufficiently by the demonstration, multiple iterations are required to recover the underlying intent of the demonstrations. However, a large number of iterations can be expensive and might not be practical for each new task. A challenge is that human-in-the-loop demonstrations can be affected by the human motor dynamics (e.g., from visual observation to hand motion), which can lead to differences between the demonstration and intent. The main contribution of this article is to correct for the human motor dynamics and infer the intended action (motion primitive) from the human demonstrations. The proposed approach uses a kernel-based regression approach to learn the inverse human-dynamics response. These models are then used to correct for human-motor-dynamics and infer the intent of the human-in-the-loop demonstrator. Experimental validation is performed with an assisted teleoperation setup where the underlying intent is specified using an augmented reality display. Results indicate that the proposed approach leads to more precise intent estimation as compared to the actual human demonstrations.

This paper studies human-guided iterative learning control for output-trajectory tracking tasks when the controller does not have direct access to the desired output and needs to infer it from human demonstrations. The main challenge is to develop such demonstration-based learning in situations where the novice human user might not be able to achieve precision tracking. The major contribution of this study is an inversion-based approach to infer the human intent and use it to design the input update for improving the output tracking. Additionally, conditions are developed for convergence of the proposed iterative output-tracking control for linear time-invariant systems. The proposed scheme is illustrated with a human-in-the-loop tracking experiment with nine human subjects. Results for each of the subjects show that the proposed human-guided learning scheme allows the machine to learn from the demonstrations and capture most of the human effort (about 90%). Moreover, the proposed approach achieves greater tracking precision (about 60% reduction in the average error) than what was achieved by the human alone.

This paper develops a provably safe on-demand conflict resolution procedure (CRP) for intersecting routes in en route air-traffic control (ATC). Recent works have developed provably safe CRPs, which solve the conflict resolution for intersecting routes in a local manner that leads to decoupling of CRPs for different intersections. However, such a CRP is inefficient because it is always on, i.e., even in the absence of conflicts. This always-on CRP (even without conflicts) leads to unwanted CRP maneuvers resulting in increased travel time, travel distance, and required fuel. This paper removes the inefficiency of always-on CRPs by developing provably safe CRPs that can be activated on demand (when conflicts appear) to accommodate an impending conflict. Conditions are developed to guarantee safety during activation and deactivation of the CRP and the proposed on-demand approach is illustrated through an example route intersection.

This paper addresses the challenge of designing provably safe conflict-resolution procedures (CRPs) that are decentralized and decoupled from each other. The main contribution of this paper is identifying necessary and sufficient conditions to decouple CRPs. Additionally, this paper demonstrates the existence of decentralized en-route CRPs that satisfy the identified decoupling conditions for each local conflict and, thereby, guarantee global conflict resolution. An advantage of the proposed CRPs is that they do not require a reduction in the aircraft flow levels in the intersecting routes for conflict resolution, which can aid in increasing the efficiency of en-route air traffic control.