In this paper, we address multi-robot formation planning where nonholonomic robots collaboratively transport objects using a deformable sheet in unstructured, cluttered environments. The formation can expand or contract to adjust the height of the object on the sheet. However, interactions between the robots and sheet introduce complex constraints for formation planning. Complexity increases further when the only feasible solution requires crossing an obstacle, i.e. where robots navigate in different homotopy classes around an obstacle such that the object hovers above it. Most existing nonholonomic formation planners do not admit obstacle crossing, limiting performance. In this paper, we present a two-stage iterative trajectory optimization framework which explicitly considers obstacle crossing. First, we capture the set of all feasible homotopy classes for each robot using a topological probabilistic roadmap. We then iteratively apply numerical optimization techniques to find a safe and feasible solution for the formation. We demonstrate the efficacy of our framework in simulation and on real robot hardware.

Behaviour trees (BTs) are popular within robotics due to their reactivity, reusability, and modularity. BTs are often designed by hand using expert domain knowledge. However, robot environments contain sources of uncertainty which affect robot behaviour. It is challenging for human designers to reason over the effects of uncertainty up to the task horizon, limiting robot performance. For example, the chance of an unexpected blockage late along a robot’s route should encourage the robot to take an alternate path. Therefore, in this paper we refine the task-level behaviour encoded in a BT through planning under uncertainty. The refinement process modifies when action nodes are executed by reasoning over the effects of uncertainty, improving task performance. We first extract a state space from the BT and learn a set of Bayesian networks (BNs) which model the stochastic dynamics of robot actions. We then use the extracted state space and BNs to construct and solve a Markov decision process which captures robot execution. This produces a policy which describes the refined behaviour. We empirically demonstrate how our approach reduces the completion time for robot navigation and search tasks.

A common task in cinematography is tracking a subject or character through a scene. For complex setups, multiple cameras must track the subject simultaneously to attain sufficient coverage. Recently, researchers have considered using multiple camera-mounted autonomous mobile robots for this task. Existing work is limited to UAVs, which may be unavailable due to cost, safety requirements, or flight restrictions. Therefore, in this paper we present a tracking approach for complex and unstructured environments using differential-drive robots with gimbal-mounted cameras. Differential-Drive robots pose a challenge, as their movement is more restricted than UAVs. For this, we introduce a novel hierarchical planning framework which ensures safety and visibility while maximizing shot diversity. We begin by synthesizing a set of paths using sequential greedy viewpoint planning and conflict-based search under a set of optimal viewpoint constraints. These paths then form an initial guess for joint trajectory optimization, which synthesizes stable trajectories under the motion constraints of the robots and gimbals. Empirically, we show how our approach outperforms approaches aimed at UAVs, which may synthesize infeasible trajectories when applied to differential-drive robots.

To efficiently cover an environment, robots must be able to handle changes in occupancy during execution. These occupancy dynamics are often stochastic, and so we cannot deterministically predict when a location will be occupied. Existing coverage solutions either assume static environments or react to changes as they occur, limiting performance. In this paper we present a framework for lifelong area coverage under spatiotemporal uncertainty, where a robot repeats coverage over multiple episodes. The stochastic occupancy dynamics are a priori unknown and learned using the observations received during coverage. For each coverage episode, we build and solve a partially observable Markov decision process which exploits our learned spatiotemporal dynamics model to improve performance. We demonstrate the efficacy of our framework across extensive experiments in synthetic environments.

For many multi-robot problems, tasks are announced during execution, where task announcement times and locations are uncertain. To synthesise multi-robot behaviour that is robust to early announcements and unexpected delays, multi-robot task allocation methods must explicitly model the stochastic processes that govern task announcement. In this paper, we model task announcement using continuous-time Markov chains which predict when and where tasks will be announced. We then present a task allocation framework which uses the continuous-time Markov chains to allocate tasks proactively, such that robots are near or at the task location upon its announcement. Our method seeks to minimise the expected total waiting duration for each task, i.e. the duration between task announcement and a robot beginning to service the task. Our framework can be applied to any multi-robot task allocation problem where robots complete spatiotemporal tasks which are announced stochastically. We demonstrate the efficacy of our approach in simulation, where we outperform baselines which do not allocate tasks proactively, or do not fully exploit our task announcement models.

Multirobot systems must be able to maintain performance when robots get delayed during execution. For mobile robots, one source of delays iscongestion. Congestion occurs when robots deployed in shared physical spaces interact, as robots present in the same area simultaneously must maneuver to avoid each other. Congestion can adversely affect navigation performance and increase the duration of navigation actions. In this article, we present a multirobot planning framework that utilizes learnt probabilistic models of how congestion affects navigation duration. Central to our framework is aprobabilistic reservation table, which summarizes robot plans, capturing the effects of congestion. To plan, we solve a sequence of single-robottime-varying Markov automata, where transition probabilities and rates are obtained from the probabilistic reservation table. We also present an iterative model refinement procedure for accurately predicting execution-time robot performance. We evaluate our framework with extensive experiments on synthetic data and simulated robot behavior.