Towards Autonomous and Safe Last-mile Deliveries with AI-augmented Self-driving Delivery Robots

In addition to its crucial impact on customer satisfaction, last-mile delivery (LMD) is notorious for being the most time-consuming and costly stage of the shipping process. Pressing environmental concerns combined with the recent surge of e-commerce sales have sparked renewed interest in automation and electrification of last-mile logistics. To address the hurdles faced by existing robotic couriers, this paper introduces a customer-centric and safety-conscious LMD system for small urban communities based on AI-assisted autonomous delivery robots. The presented framework enables end-to-end automation and optimization of the logistic process while catering for real-world imposed operational uncertainties, clients' preferred time schedules, and safety of pedestrians. To this end, the integrated optimization component is modeled as a robust variant of the Cumulative Capacitated Vehicle Routing Problem with Time Windows, where routes are constructed under uncertain travel times with an objective to minimize the total latency of deliveries (i.e., the overall waiting time of customers, which can negatively affect their satisfaction). We demonstrate the proposed LMD system's utility through real-world trials in a university campus with a single robotic courier. Implementation aspects as well as the findings and practical insights gained from the deployment are discussed in detail. Lastly, we round up the contributions with numerical simulations to investigate the scalability of the developed mathematical formulation with respect to the number of robotic vehicles and customers.

DClEVerNet: Deep Combinatorial Learning for Efficient EV Charging Scheduling in Large-scale Networked Facilities

With the electrification of transportation, the rising uptake of electric vehicles (EVs) might stress distribution networks significantly, leaving their performance degraded and stability jeopardized. To accommodate these new loads cost-effectively, modern power grids require coordinated or ``smart'' charging strategies capable of optimizing EV charging scheduling in a scalable and efficient fashion. With this in view, the present work focuses on reservation management programs for large-scale, networked EV charging stations. We formulate a time-coupled binary optimization problem that maximizes EV users' total welfare gain while accounting for the network's available power capacity and stations' occupancy limits. To tackle the problem at scale while retaining high solution quality, a data-driven optimization framework combining techniques from the fields of Deep Learning and Approximation Algorithms is introduced. The framework's key ingredient is a novel input-output processing scheme for neural networks that allows direct extrapolation to problem sizes substantially larger than those included in the training set. Extensive numerical simulations based on synthetic and real-world data traces verify the effectiveness and superiority of the presented approach over two representative scheduling algorithms. Lastly, we round up the contributions by listing several immediate extensions to the proposed framework and outlining the prospects for further exploration.

DFR-FastMOT: Detection Failure Resistant Tracker for Fast Multi-Object Tracking Based on Sensor Fusion

Persistent multi-object tracking (MOT) allows autonomous vehicles to navigate safely in highly dynamic environments. One of the well-known challenges in MOT is object occlusion when an object becomes unobservant for subsequent frames. The current MOT methods store objects information, like objects' trajectory, in internal memory to recover the objects after occlusions. However, they retain short-term memory to save computational time and avoid slowing down the MOT method. As a result, they lose track of objects in some occlusion scenarios, particularly long ones. In this paper, we propose DFR-FastMOT, a light MOT method that uses data from a camera and LiDAR sensors and relies on an algebraic formulation for object association and fusion. The formulation boosts the computational time and permits long-term memory that tackles more occlusion scenarios. Our method shows outstanding tracking performance over recent learning and non-learning benchmarks with about 3% and 4% margin in MOTA, respectively. Also, we conduct extensive experiments that simulate occlusion phenomena by employing detectors with various distortion levels. The proposed solution enables superior performance under various distortion levels in detection over current state-of-art methods. Our framework processes about 7,763 frames in 1.48 seconds, which is seven times faster than recent benchmarks. The framework will be available at https://github.com/MohamedNagyMostafa/DFR-FastMOT.

Dual Formulation for Chance Constrained Stochastic Shortest Path with Application to Autonomous Vehicle Behavior Planning

Autonomous vehicles face the problem of optimizing the expected performance of subsequent maneuvers while bounding the risk of collision with surrounding dynamic obstacles. These obstacles, such as agent vehicles, often exhibit stochastic transitions that should be accounted for in a timely and safe manner. The Constrained Stochastic Shortest Path problem (C-SSP) is a formalism for planning in stochastic environments under certain types of operating constraints. While C-SSP allows specifying constraints in the planning problem, it does not allow for bounding the probability of constraint violation, which is desired in safety-critical applications. This work's first contribution is an exact integer linear programming formulation for Chance-constrained SSP (CC-SSP) that attains deterministic policies. Second, a randomized rounding procedure is presented for stochastic policies. Third, we show that the CC-SSP formalism can be generalized to account for constraints that span through multiple time steps. Evaluation results show the usefulness of our approach in benchmark problems compared to existing approaches.

Building Resilience to Out-of-Distribution Visual Data via Input Optimization and Model Finetuning

A major challenge in machine learning is resilience to out-of-distribution data, that is data that exists outside of the distribution of a model's training data. Training is often performed using limited, carefully curated datasets and so when a model is deployed there is often a significant distribution shift as edge cases and anomalies not included in the training data are encountered. To address this, we propose the Input Optimisation Network, an image preprocessing model that learns to optimise input data for a specific target vision model. In this work we investigate several out-of-distribution scenarios in the context of semantic segmentation for autonomous vehicles, comparing an Input Optimisation based solution to existing approaches of finetuning the target model with augmented training data and an adversarially trained preprocessing model. We demonstrate that our approach can enable performance on such data comparable to that of a finetuned model, and subsequently that a combined approach, whereby an input optimization network is optimised to target a finetuned model, delivers superior performance to either method in isolation. Finally, we propose a joint optimisation approach, in which input optimization network and target model are trained simultaneously, which we demonstrate achieves significant further performance gains, particularly in challenging edge-case scenarios. We also demonstrate that our architecture can be reduced to a relatively compact size without a significant performance impact, potentially facilitating real time embedded applications.

Multi-Agent Chance-Constrained Stochastic Shortest Path with Application to Risk-Aware Intelligent Intersection

In transportation networks, where traffic lights have traditionally been used for vehicle coordination, intersections act as natural bottlenecks. A formidable challenge for existing automated intersections lies in detecting and reasoning about uncertainty from the operating environment and human-driven vehicles. In this paper, we propose a risk-aware intelligent intersection system for autonomous vehicles (AVs) as well as human-driven vehicles (HVs). We cast the problem as a novel class of Multi-agent Chance-Constrained Stochastic Shortest Path (MCC-SSP) problems and devise an exact Integer Linear Programming (ILP) formulation that is scalable in the number of agents' interaction points (e.g., potential collision points at the intersection). In particular, when the number of agents within an interaction point is small, which is often the case in intersections, the ILP has a polynomial number of variables and constraints. To further improve the running time performance, we show that the collision risk computation can be performed offline. Additionally, a trajectory optimization workflow is provided to generate risk-aware trajectories for any given intersection. The proposed framework is implemented in CARLA simulator and evaluated under a fully autonomous intersection with AVs only as well as in a hybrid setup with a signalized intersection for HVs and an intelligent scheme for AVs. As verified via simulations, the featured approach improves intersection's efficiency by up to $200\%$ while also conforming to the specified tunable risk threshold.

A Fully Polynomial Time Approximation Scheme for Fixed-Horizon Constrained Stochastic Shortest Path Problem under Local Transitions

The fixed-horizon constrained stochastic shortest path problem (C-SSP) is a formalism for planning in stochastic environments under certain operating constraints. Chance-Constrained SSP (CC-SSP) is a variant that allows bounding the probability of constraint violation, which is desired in many safety-critical applications. This work considers an important variant of (C)C-SSP under local transition, capturing a broad class of SSP problems where state reachability exhibit a certain locality. Only a constant number of states can share some subsequent states. (C)C-SSP under local transition is NP-Hard even for a planning horizon of two. In this work, we propose a fully polynomial-time approximation scheme for (C)C-SSP that computes (near) optimal deterministic policies. Such an algorithm is the best approximation algorithm attainable in theory

Risk-Aware Reasoning for Autonomous Vehicles

A significant barrier to deploying autonomous vehicles (AVs) on a massive scale is safety assurance. Several technical challenges arise due to the uncertain environment in which AVs operate such as road and weather conditions, errors in perception and sensory data, and also model inaccuracy. In this paper, we propose a system architecture for risk-aware AVs capable of reasoning about uncertainty and deliberately bounding the risk of collision below a given threshold. We discuss key challenges in the area, highlight recent research developments, and propose future research directions in three subsystems. First, a perception subsystem that detects objects within a scene while quantifying the uncertainty that arises from different sensing and communication modalities. Second, an intention recognition subsystem that predicts the driving-style and the intention of agent vehicles (and pedestrians). Third, a planning subsystem that takes into account the uncertainty, from perception and intention recognition subsystems, and propagates all the way to control policies that explicitly bound the risk of collision. We believe that such a white-box approach is crucial for future adoption of AVs on a large scale.

Autonomous Recharging and Flight Mission Planning for Battery-operated Autonomous Drones

Autonomous drones (also known as unmanned aerial vehicles) are increasingly popular for diverse applications of light-weight delivery and as substitutions of manned operations in remote locations. The computing systems for drones are becoming a new venue for research in cyber-physical systems. Autonomous drones require integrated intelligent decision systems to control and manage their flight missions in the absence of human operators. One of the most crucial aspects of drone mission control and management is related to the optimization of battery lifetime. Typical drones are powered by on-board batteries, with limited capacity. But drones are expected to carry out long missions. Thus, a fully automated management system that can optimize the operations of battery-operated autonomous drones to extend their operation time is highly desirable. This paper presents several contributions to automated management systems for battery-operated drones: (1) We conduct empirical studies to model the battery performance of drones, considering various flight scenarios. (2) We study a joint problem of flight mission planning and recharging optimization for drones with an objective to complete a tour mission for a set of sites of interest in the shortest time. This problem captures diverse applications of delivery and remote operations by drones. (3) We present algorithms for solving the problem of flight mission planning and recharging optimization. We implemented our algorithms in a drone management system, which supports real-time flight path tracking and re-computation in dynamic environments. We evaluated the results of our algorithms using data from empirical studies. (4) To allow fully autonomous recharging of drones, we also develop a robotic charging system prototype that can recharge drones autonomously by our drone management system.