arXiv subjects

Javier Alonso-Mora

Publications and source records attributed to Javier Alonso-Mora.

At least 91 records · Page 5Linked to original sources

arXiv2022

Wi-Closure: Reliable and Efficient Search of Inter-robot Loop Closures Using Wireless Sensing

In this paper we propose a novel algorithm, Wi-Closure, to improve computational efficiency and robustness of loop closure detection in multi-robot SLAM. Our approach decreases the computational overhead of classical approaches by pruning the search space of potential loop closures, prior to evaluation by a typical multi-robot SLAM pipeline. Wi-Closure achieves this by identifying candidates that are spatially close to each other by using sensing over the wireless communication signal between robots, even when they are operating in non-line-of-sight or in remote areas of the environment from one another. We demonstrate the validity of our approach in simulation and hardware experiments. Our results show that using Wi-closure greatly reduces computation time, by 54% in simulation and by 77% in hardware compared, with a multi-robot SLAM baseline. Importantly, this is achieved without sacrificing accuracy. Using Wi-Closure reduces absolute trajectory estimation error by 99% in simulation and 89.2% in hardware experiments. This improvement is due in part to Wi-Closure's ability to avoid catastrophic optimization failure that typically occurs with classical approaches in challenging repetitive environments.

cs.RO↗

arXiv2022

Local Planner Bench: Benchmarking for Local Motion Planning

Local motion planning is a heavily researched topic in the field of robotics with many promising algorithms being published every year. However, it is difficult and time-consuming to compare different methods in the field. In this paper, we present localPlannerBench, a new benchmarking suite that allows quick and seamless comparison between local motion planning algorithms. The key focus of the project lies in the extensibility of the environment and the simulation cases. Out-of-the-box, localPlannerBench already supports many simulation cases ranging from a simple 2D point mass to full-fledged 3D 7DoF manipulators, and it is straightforward to add your own custom robot using a URDF file. A post-processor is built-in that can be extended with custom metrics and plots. To integrate your own motion planner, simply create a wrapper that derives from the provided base class. Ultimately we aim to improve the reproducibility of local motion planning algorithms and encourage standardized open-source comparison.

cs.RO↗

arXiv2022

Error-Bounded Approximation of Pareto Fronts in Robot Planning Problems

Many problems in robotics seek to simultaneously optimize several competing objectives under constraints. A conventional approach to solving such multi-objective optimization problems is to create a single cost function comprised of the weighted sum of the individual objectives. Solutions to this scalarized optimization problem are Pareto optimal solutions to the original multi-objective problem. However, finding an accurate representation of a Pareto front remains an important challenge. Using uniformly spaced weight vectors is often inefficient and does not provide error bounds. Thus, we address the problem of computing a finite set of weight vectors such that for any other weight vector, there exists an element in the set whose error compared to optimal is minimized. To this end, we prove fundamental properties of the optimal cost as a function of the weight vector, including its continuity and concavity. Using these, we propose an algorithm that greedily adds the weight vector least-represented by the current set, and provide bounds on the error. Finally, we illustrate that the proposed approach significantly outperforms uniformly distributed weights for different robot planning problems with varying numbers of objective functions.

cs.RO↗

arXiv2022

Multi-robot Task Assignment for Aerial Tracking with Viewpoint Constraints

We address the problem of assigning a team of drones to autonomously capture a set desired shots of a dynamic target in the presence of obstacles. We present a two-stage planning pipeline that generates offline an assignment of drone to shots and locally optimizes online the viewpoint. Given desired shot parameters, the high-level planner uses a visibility heuristic to predict good times for capturing each shot and uses an Integer Linear Program to compute drone assignments. An online Model Predictive Control algorithm uses the assignments as reference to capture the shots. The algorithm is validated in hardware with a pair of drones and a remote controlled car.

cs.RO↗

arXiv2022

Learning Mixed Strategies in Trajectory Games

In multi-agent settings, game theory is a natural framework for describing the strategic interactions of agents whose objectives depend upon one another's behavior. Trajectory games capture these complex effects by design. In competitive settings, this makes them a more faithful interaction model than traditional "predict then plan" approaches. However, current game-theoretic planning methods have important limitations. In this work, we propose two main contributions. First, we introduce an offline training phase which reduces the online computational burden of solving trajectory games. Second, we formulate a lifted game which allows players to optimize multiple candidate trajectories in unison and thereby construct more competitive "mixed" strategies. We validate our approach on a number of experiments using the pursuit-evasion game "tag."

cs.GT↗

arXiv2022

Prediction-Based Reachability Analysis for Collision Risk Assessment on Highways

Real-time safety systems are crucial components of intelligent vehicles. This paper introduces a prediction-based collision risk assessment approach on highways. Given a point mass vehicle dynamics system, a stochastic forward reachable set considering two-dimensional motion with vehicle state probability distributions is firstly established. We then develop an acceleration prediction model, which provides multi-modal probabilistic acceleration distributions to propagate vehicle states. The collision probability is calculated by summing up the probabilities of the states where two vehicles spatially overlap. Simulation results show that the prediction model has superior performance in terms of vehicle motion position errors, and the proposed collision detection approach is agile and effective to identify the collision in cut-in crash events.

eess.SY↗

arXiv2022

Where to Look Next: Learning Viewpoint Recommendations for Informative Trajectory Planning

Search missions require motion planning and navigation methods for information gathering that continuously replan based on new observations of the robot's surroundings. Current methods for information gathering, such as Monte Carlo Tree Search, are capable of reasoning over long horizons, but they are computationally expensive. An alternative for fast online execution is to train, offline, an information gathering policy, which indirectly reasons about the information value of new observations. However, these policies lack safety guarantees and do not account for the robot dynamics. To overcome these limitations we train an information-aware policy via deep reinforcement learning, that guides a receding-horizon trajectory optimization planner. In particular, the policy continuously recommends a reference viewpoint to the local planner, such that the resulting dynamically feasible and collision-free trajectories lead to observations that maximize the information gain and reduce the uncertainty about the environment. In simulation tests in previously unseen environments, our method consistently outperforms greedy next-best-view policies and achieves competitive performance compared to Monte Carlo Tree Search, in terms of information gains and coverage time, with a reduction in execution time by three orders of magnitude.

cs.RO↗

arXiv2022

Improving Pedestrian Prediction Models with Self-Supervised Continual Learning

Autonomous mobile robots require accurate human motion predictions to safely and efficiently navigate among pedestrians, whose behavior may adapt to environmental changes. This paper introduces a self-supervised continual learning framework to improve data-driven pedestrian prediction models online across various scenarios continuously. In particular, we exploit online streams of pedestrian data, commonly available from the robot's detection and tracking pipeline, to refine the prediction model and its performance in unseen scenarios. To avoid the forgetting of previously learned concepts, a problem known as catastrophic forgetting, our framework includes a regularization loss to penalize changes of model parameters that are important for previous scenarios and retrains on a set of previous examples to retain past knowledge. Experimental results on real and simulation data show that our approach can improve prediction performance in unseen scenarios while retaining knowledge from seen scenarios when compared to naively training the prediction model online.

cs.RO↗

arXiv2022

Decentralized Probabilistic Multi-Robot Collision Avoidance Using Buffered Uncertainty-Aware Voronoi Cells

In this paper, we present a decentralized and communication-free collision avoidance approach for multi-robot systems that accounts for both robot localization and sensing uncertainties. The approach relies on the computation of an uncertainty-aware safe region for each robot to navigate among other robots and static obstacles in the environment, under the assumption of Gaussian-distributed uncertainty. In particular, at each time step, we construct a chance-constrained buffered uncertainty-aware Voronoi cell (B-UAVC) for each robot given a specified collision probability threshold. Probabilistic collision avoidance is achieved by constraining the motion of each robot to be within its corresponding B-UAVC, i.e. the collision probability between the robots and obstacles remains below the specified threshold. The proposed approach is decentralized, communication-free, scalable with the number of robots and robust to robots' localization and sensing uncertainties. We applied the approach to single-integrator, double-integrator, differential-drive robots, and robots with general nonlinear dynamics. Extensive simulations and experiments with a team of ground vehicles, quadrotors, and heterogeneous robot teams are performed to analyze and validate the proposed approach.

cs.RO↗

arXiv2021

Integrated Task Assignment and Path Planning for Capacitated Multi-Agent Pickup and Delivery

Multi-agent Pickup and Delivery (MAPD) is a challenging industrial problem where a team of robots is tasked with transporting a set of tasks, each from an initial location and each to a specified target location. Appearing in the context of automated warehouse logistics and automated mail sortation, MAPD requires first deciding which robot is assigned what task (i.e., Task Assignment or TA) followed by a subsequent coordination problem where each robot must be assigned collision-free paths so as to successfully complete its assignment (i.e., Multi-Agent Path Finding or MAPF). Leading methods in this area solve MAPD sequentially: first assigning tasks, then assigning paths. In this work we propose a new coupled method where task assignment choices are informed by actual delivery costs instead of by lower-bound estimates. The main ingredients of our approach are a marginal-cost assignment heuristic and a meta-heuristic improvement strategy based on Large Neighbourhood Search. As a further contribution, we also consider a variant of the MAPD problem where each robot can carry multiple tasks instead of just one. Numerical simulations show that our approach yields efficient and timely solutions and we report significant improvement compared with other recent methods from the literature.

cs.MA↗

arXiv2021

New sources of economies and diseconomies of scale in on-demand ridepooling systems and comparison with public transport

On-demand ridepooling (ODRP) can become a powerful alternative to reduce congestion and emissions, if it attracts private car users. Therefore, it is crucial to identify the strategic phenomena that determine when ODRP systems can run efficiently. In this paper, we analyze the performance of an ODRP system, in which the fleet of low-capacity vehicles is endogenously adapted to the demand, and operated in a zone covered by a single transit line. The routing of the on-demand fleet follows some of the rules of public transport systems; namely, it is not-for-profit, some users can be required to walk, and all requests must be served. Considering both users' and operators' costs we identify two sources of scale economies: when demand grows, the average cost is reduced due to a) an equivalent of the Mohring Effect (also present in public transport), and b) due to matching users with more similar routes when they are assigned to the vehicles, which we call Better-matching Effect. A counter-balance force, called Flex-route Effect, is observed when the vehicle loads increase and users face longer detours. We find a specific demand range in which the latter effect dominates the others, imposing diseconomies of scale when only users' costs are considered. Such a phenomenon emerges because the routes are not fixed; hence, it is not observed in traditional public transport systems. However, when considering both users' and operators' costs, scale economies prevail. Our simulations show that relaxing door-to-door vehicle requirements to allow short walks is crucial for the performance of ODRP. In fact, we observe that an ODRP system with human-driven vehicles and walks allowed has a total cost at a similar level to that of a door-to-door ODRP system with driverless vehicles.

physics.soc-ph↗

arXiv2021

Ride-Pooling Matching with a Compensatory Cost Function: Implications for Adoption, Efficiency and Level of Service

By utilising vehicle capacity more efficiently, ride-pooling platforms can potentially lead to reduced congestion levels without adversely prolonging travel times. While previous studies concluded that shared rides can offer substantial benefits, initial evidence suggests low adoption levels. We postulate that previous studies that investigated the potential of ride-pooling failed to account for the trade-off that users are likely to make when considering a shared ride. We address this shortcoming by formulating user net benefit stemming from sharing as a compensatory function where the additional travel time and on-board discomfort need to be compensated by the price discount for a traveller to choose a shared ride over a private ride. The proposed formulation is embedded in a method for matching travel requests and vehicles. We conduct a series of experiments investigating how the potential of ride-pooling services depends on travel demand characteristics, user preferences and the pricing policy adopted by the service provider. In particular, the impact of various behavioural settings in terms of users' willingness to share their ride and delay aversion on service adoption and its operational efficiency is assessed. Our results suggest that the total vehicle mileage savings found by previous studies is only attainable when users are very willing to share their ride (i.e. attach low premium to private rides) and are offered a 50% discount for doing so. We find ride-pooling transportation distance savings as low as 15% in less favourable behavioural scenarios.

physics.soc-ph↗

arXiv2021

Learning Interaction-aware Guidance Policies for Motion Planning in Dense Traffic Scenarios

Autonomous navigation in dense traffic scenarios remains challenging for autonomous vehicles (AVs) because the intentions of other drivers are not directly observable and AVs have to deal with a wide range of driving behaviors. To maneuver through dense traffic, AVs must be able to reason how their actions affect others (interaction model) and exploit this reasoning to navigate through dense traffic safely. This paper presents a novel framework for interaction-aware motion planning in dense traffic scenarios. We explore the connection between human driving behavior and their velocity changes when interacting. Hence, we propose to learn, via deep Reinforcement Learning (RL), an interaction-aware policy providing global guidance about the cooperativeness of other vehicles to an optimization-based planner ensuring safety and kinematic feasibility through constraint satisfaction. The learned policy can reason and guide the local optimization-based planner with interactive behavior to pro-actively merge in dense traffic while remaining safe in case the other vehicles do not yield. We present qualitative and quantitative results in highly interactive simulation environments (highway merging and unprotected left turns) against two baseline approaches, a learning-based and an optimization-based method. The presented results demonstrate that our method significantly reduces the number of collisions and increases the success rate with respect to both learning-based and optimization-based baselines.

cs.RO↗

arXiv2021

Anticipatory routing methods for an on-demand ridepooling mobility system

One of the most relevant challenges regarding on-demand ridepooling relates to the spatial imbalances of the demand, which induce a mismatch between the position of the vehicles and the origins of the emerging requests. Most ridepooling models face this problem through rebalancing methods only, i.e., moving idle vehicles towards areas with high rejections rate, which is done independently from routing and vehicle-to-orders assignments, so that vehicles serving passengers (a large portion of the total fleet) remain unaffected. This paper introduces two types of techniques for anticipatory routing that affect how vehicles are assigned to users and how to route vehicles to serve such users, so that the whole operation of the system is modified to reach more efficient states for future requests. Both techniques do not require any assumption or exogenous knowledge about the future demand, as they depend only on current and recent requests. Firstly, we introduce rewards that reduce the cost of an assignment between a vehicle and a group of passengers if the vehicle gets routed towards a high-demand zone. Secondly, we include a small set of artificial requests, whose request times are in the near future and whose origins are sampled from a probability distribution that mimics observed generation rates. These artificial requests are to be assigned together with the real requests. We test these techniques using a set of real rides from Manhattan. Introducing rewards can diminish the rejection rate to about nine-tenths of its original value. On the other hand, including future requests can reduce users' traveling times by about one-fifth, but increasing rejections. Both methods increase the vehicles-hour-traveled by about 10%. Spatial analysis reveals that vehicles are indeed moved towards the most demanded areas, such that the reduction in rejections rate is achieved mostly there.

eess.SY↗

arXiv2021

How to split the costs among travellers sharing a ride? Aligning system's optimum with users' equilibrium

How to form groups in a mobility system that offers shared rides, and how to split the costs within the travellers of a group, are non-trivial tasks, as two objectives conflict: 1) minimising the total costs of the system, and 2) making each user content with her assignment. Aligning both objectives is challenging, as users are not aware of the externalities induced to the rest of the system. In this paper, we propose protocols to share the costs within a ride so that optimal solutions can also constitute equilibria. To do this, we model the situation as a game. We show that the traditional notions of equilibrium in game theory (Nash and Strong) are not useful here, and prove that determining whether a Strong Equilibrium exists is an NP-Complete problem. Hence, we propose three alternative equilibrium notions (stronger than Nash and weaker than Strong), depending on how users can coordinate, that effectively represent stable ways to match the users. We then propose three cost-sharing protocols, for which the optimal solutions are an equilibrium for each of the mentioned intermediate notions of equilibrium. The game we study can be seen as a game-version of the well-known \textit{set cover problem}. Numerical simulations for Amsterdam reveal that our protocols can achieve stable solutions that are always close to the optimum, that there exists a trade-off between total users' costs and how equal do they distribute among them, and that having a central coordinator can have a large impact.

cs.GT↗

arXiv2021

Online Informative Path Planning for Active Information Gathering of a 3D Surface

This paper presents an online informative path planning approach for active information gathering on three-dimensional surfaces using aerial robots. Most existing works on surface inspection focus on planning a path offline that can provide full coverage of the surface, which inherently assumes the surface information is uniformly distributed hence ignoring potential spatial correlations of the information field. In this paper, we utilize manifold Gaussian processes (mGPs) with geodesic kernel functions for mapping surface information fields and plan informative paths online in a receding horizon manner. Our approach actively plans information-gathering paths based on recent observations that respect dynamic constraints of the vehicle and a total flight time budget. We provide planning results for simulated temperature modeling for simple and complex 3D surface geometries (a cylinder and an aircraft model). We demonstrate that our informative planning method outperforms traditional approaches such as 3D coverage planning and random exploration, both in reconstruction error and information-theoretic metrics. We also show that by taking spatial correlations of the information field into planning using mGPs, the information gathering efficiency is significantly improved.

cs.RO↗

arXiv2021

Where to go next: Learning a Subgoal Recommendation Policy for Navigation Among Pedestrians

Robotic navigation in environments shared with other robots or humans remains challenging because the intentions of the surrounding agents are not directly observable and the environment conditions are continuously changing. Local trajectory optimization methods, such as model predictive control (MPC), can deal with those changes but require global guidance, which is not trivial to obtain in crowded scenarios. This paper proposes to learn, via deep Reinforcement Learning (RL), an interaction-aware policy that provides long-term guidance to the local planner. In particular, in simulations with cooperative and non-cooperative agents, we train a deep network to recommend a subgoal for the MPC planner. The recommended subgoal is expected to help the robot in making progress towards its goal and accounts for the expected interaction with other agents. Based on the recommended subgoal, the MPC planner then optimizes the inputs for the robot satisfying its kinodynamic and collision avoidance constraints. Our approach is shown to substantially improve the navigation performance in terms of number of collisions as compared to prior MPC frameworks, and in terms of both travel time and number of collisions compared to deep RL methods in cooperative, competitive and mixed multiagent scenarios.

cs.RO↗

arXiv2021

Learning Interaction-Aware Trajectory Predictions for Decentralized Multi-Robot Motion Planning in Dynamic Environments

This paper presents a data-driven decentralized trajectory optimization approach for multi-robot motion planning in dynamic environments. When navigating in a shared space, each robot needs accurate motion predictions of neighboring robots to achieve predictive collision avoidance. These motion predictions can be obtained among robots by sharing their future planned trajectories with each other via communication. However, such communication may not be available nor reliable in practice. In this paper, we introduce a novel trajectory prediction model based on recurrent neural networks (RNN) that can learn multi-robot motion behaviors from demonstrated trajectories generated using a centralized sequential planner. The learned model can run efficiently online for each robot and provide interaction-aware trajectory predictions of its neighbors based on observations of their history states. We then incorporate the trajectory prediction model into a decentralized model predictive control (MPC) framework for multi-robot collision avoidance. Simulation results show that our decentralized approach can achieve a comparable level of performance to a centralized planner while being communication-free and scalable to a large number of robots. We also validate our approach with a team of quadrotors in real-world experiments.

cs.RO↗