Brandon Douglas Luders

Probabilistically safe motion planning to avoid dynamic obstacles with uncertain motion patterns

This paper presents a real-time path planning algorithm that guarantees probabilistic feasibility for autonomous robots with uncertain dynamics operating amidst one or more dynamic obstacles with uncertain motion patterns. Planning safe trajectories under such conditions requires both accurate prediction and proper integration of future obstacle behavior within the planner. Given that available observation data is limited, the motion model must provide generalizable predictions that satisfy dynamic and environmental constraints, a limitation of existing approaches. This work presents a novel solution, named RR-GP, which builds a learned motion pattern model by combining the flexibility of Gaussian processes (GP) with the efficiency of RRT-Reach, a sampling-based reachability computation. Obstacle trajectory GP predictions are conditioned on dynamically feasible paths identified from the reachability analysis, yielding more accurate predictions of future behavior. RR-GP predictions are integrated with a robust path planner, using chance-constrained RRT, to identify probabilistically feasible paths. Theoretical guarantees of probabilistic feasibility are shown for linear systems under Gaussian uncertainty; approximations for nonlinear dynamics and/or non-Gaussian uncertainty are also presented. Simulations demonstrate that, with this planner, an autonomous vehicle can safely navigate a complex environment in real-time while significantly reducing the risk of collisions with dynamic obstacles.

A voice-commandable robotic forklift working alongside humans in minimally-prepared outdoor environments

One long-standing challenge in robotics is the realization of mobile autonomous robots able to operate safely in existing human workplaces in a way that their presence is accepted by the human occupants. We describe the development of a multi-ton robotic forklift intended to operate alongside human personnel, handling palletized materials within existing, busy, semi-structured outdoor storage facilities.

Chance Constrained RRT for Probabilistic Robustness to Environmental Uncertainty

between planner conservatism and the risk of infeasibility. This paper presents a novel real-time planning algorithm, chance constrained rapidly-exploring random trees (CC-RRT), which uses chance constraints to guarantee probabilistic feasibility for linear systems subject to process noise and/or uncertain, possibly dynamic obstacles. By using RRT, the algorithm enjoys the computational benets of sampling-based algorithms, such as trajectory-wise constraint checking and incorporation of heuristics, while explicitly incorporating uncertainty within the formulation. Under the assumption of Gaussian noise, probabilistic feasibility at each time step can be established through simple simulation of the state conditional mean and the evaluation of linear constraints. Alternatively, a small amount of additional computation can be used to explicitly compute a less conservative probability bound at each time step. Simulation results show that this algorithm can be used for ecient identication and execution of probabilistically safe paths in real time.

Information-rich Path Planning with General Constraints using Rapidly-exploring Random Trees

This paper introduces the Information-rich Rapidly-exploring Random Tree (IRRT), an extension of the RRT algorithm that embeds information collection as predicted using Fisher Information Matrices. The primary contribution of this algorithm is target-based information maximization in general (possibly heavily constrained) environments, with complex vehicle dynamic constraints and sensor limitations, including limited resolution and narrow eld-of-view. An extension of IRRT for multi-agent missions is also presented. IRRT is distinguished from previous solutions strategies by its computational tractability and general constraint characterization. A progression of simulation results demonstrates that this implementation can generate complex target-tracking behaviors from a simple model of the trade-o between information gathering and goal arrival.

Robust Sampling-based Motion Planning with Asymptotic Optimality Guarantees

This paper presents a novel sampling-based planner, CC-RRT*, which generates robust, asymptotically optimal trajectories in real-time for linear Gaussian systems subject to process noise, localization error, and uncertain environmental constraints. CC-RRT* provides guaranteed probabilistic feasibility, both at each time step and along the entire trajectory, by using chance constraints to efficiently approximate the risk of constraint violation. This algorithm expands on existing results by utilizing the framework of RRT* to provide guarantees on asymptotic optimality of the lowest-cost probabilistically feasible path found. A novel riskbased objective function, shown to be admissible within RRT*, allows the user to trade-off between minimizing path duration and risk-averse behavior. This enables the modeling of soft risk constraints simultaneously with hard probabilistic feasibility bounds. Simulation results demonstrate that CC-RRT* can efficiently identify smooth, robust trajectories for a variety of uncertainty scenarios and dynamics.

Bounds on tracking error using closed-loop rapidly-exploring random trees

This paper considers the real-time motion planning problem for autonomous systems subject to complex dynamics, constraints, and uncertainty. Rapidly-exploring random trees (RRT) can be used to efficiently construct trees of dynamically feasible trajectories; however, to ensure feasibility, it is critical that the system actually track its predicted trajectory. This paper shows that under certain assumptions, the recently proposed closed-loop RRT (CL-RRT) algorithm can be used to accurately track a trajectory with known error bounds and robust feasibility guarantees, without the need for replanning. Unlike open-loop approaches, bounds can be designed on the maximum prediction error for a known uncertainty distribution. Using the property that a stabilized linear system subject to bounded process noise has BIBO-stable error dynamics, this paper shows how to modify the problem constraints to ensure long-term feasibility under uncertainty. Simulation results are provided to demonstrate the effectiveness of the closed-loop RRT approach compared to open-loop alternatives.

Threat-aware path planning in uncertain urban environments

This paper considers the path planning problem for an autonomous vehicle in an urban environment populated with static obstacles and moving vehicles with uncertain intents. We propose a novel threat assessment module, consisting of an intention predictor and a threat assessor, which augments the host vehicles path planner with a real-time threat value representing the risks posed by the estimated intentions of other vehicles. This new threat-aware planning approach is applied to the CL-RRT path planning framework, used by the MIT team in the 2007 DARPA Grand Challenge. The strengths of this approach are demonstrated through simulation and experiments performed in the RAVEN testbed facilities.

Information-Theoretic Motion Planning for Constrained Sensor Networks

This paper considers the problem of online informative motion planning for a network of heterogeneous mobile sensing agents, each subject to dynamic constraints, environmental constraints, and sensor limitations. Previous work has not yielded algorithms that are amenable to such general constraint characterizations. In this paper, the information-rich rapidly-exploring random tree algorithm is proposed as a solution to the constrained informative motion planning problem that embeds metrics on uncertainty reduction at both the tree growth and path selection levels. The proposed algorithm possesses a number of beneficial properties, chief among them being the ability to quickly find dynamically feasible, informative paths, even subject to the aforementioned constraints. The utility of the proposed algorithm in efficiently localizing stationary targets is demonstrated in a progression of simulation results with both single-agent and multiagent networks. These results show that the information-rich rapidly-ex...

Robust Trajectory Planning for Autonomous Parafoils under Wind Uncertainty

A key challenge facing modern airborne delivery systems, such as parafoils, is the ability to accurately and consistently deliver supplies into difficult, complex terrain. Robustness is a primary concern, given that environmental wind disturbances are often highly uncertain and time-varying, coupled with under-actuated dynamics and potentially narrow drop zones. This paper presents a new on-line trajectory planning algorithm that enables a large, autonomous parafoil to robustly execute collision avoidance and precision landing on mapped terrain, even with significant wind uncertainties. This algorithm is designed to handle arbitrary initial altitudes, approach geometries, and terrain surfaces, and is robust to wind disturbances which may be highly dynamic throughout the terminal approach. Explicit, real-time wind modeling and classification is used to anticipate future disturbances, while a novel uncertainty-sampling technique ensures that robustness to possible future variation is efficiently maintained. The designed cost-to-go function enables selection of partial paths which intelligently trade off between current and reachable future states. Simulation results demonstrate that the proposed algorithm reduces the worst-case impact of wind disturbances relative to state-of-the-art approaches.

Sampling-Based Threat Assessment Algorithms for Intersection Collisions Involving Errant Drivers

Abstract This paper considers the decision-making problem for a vehicle crossing a road intersection in the presence of other, potentially errant, drivers. This problem is considered in a game-theoretic framework, where the errant drivers are assumed to be capable of causing intentional collisions. Our approach is to simulate the possible behaviors of errant drivers using RRT-Reach, a modified application of rapidly-exploring random trees. A novelty in RRT-Reach is the use of a dual exploration-pursuit mode, which allows for efficient approximation of the errant reachability set for some fixed time horizon. Through simulation and experimental results with a small autonomous vehicle, we demonstrate that this threat assessment algorithm can be used in real-time to minimize the risk of collision.