Behavior planning in urban environments must consider the various existing uncertainties in an explicit way. This work proposes a behavior planner, based on a POMDP formulation, that explicitly considers possibly occluded vehicles. The future field of view of the autonomous car is predicted over the whole planning horizon. Both, occlusions which are generated by static as well as generated by dynamic objects are hereby considered. We use Monte Carlo sampling to generate possible future episodes that are used to derive an optimized policy. The sampled episodes consider the uncertain behavior of the known traffic participants as well as the existence probability of so-called phantom vehicles in occluded areas. By representing all possible, occluded vehicle configurations by its reachable set instead of single particles, a very efficient representation is found. Therefore, we ensure to consider all possible configurations which may drive out of the occluded area in our optimized policy. We propose a generic formulation of the POMDP problem that can be applied to various scenarios for urban driving. Its performance is demonstrated by using simulation scenarios at intersections including multiple vehicles and occlusions caused by static and dynamic objects. It is shown, that the autonomous vehicle approaches occluded areas by far less conservative than a baseline strategy which considers only the current field of view (fov). This is because various, future scenarios are already considered in the policy. In fact, we show that our planner is able to drive nearly the same trajectories as an omniscient planner would.

Autonomous driving requires decision making in dynamic and uncertain environments. The uncertainty from the prediction originates from the noisy sensor data and from the fact that the intention of human drivers cannot be directly measured. This problem is formulated as a partially observable Markov decision process (POMDP) with the intention of the other vehicles as hidden variables. The solution of the POMDP is a policy determining the optimal acceleration of the ego vehicle along a preplanned path. Therefore, the policy is optimized for the most likely future scenarios resulting from an interactive, probabilistic motion model for the other vehicles. Considering possible future measurements of the surroundings allows the autonomous car to incorporate the estimated change in future prediction accuracy in the optimal policy. A compact representation allows a low-dimensional state-space so that the problem can be solved online for varying road layouts and number of other vehicles. This is done with a point-based solver in an anytime fashion on a continuous state-space. We show the results with simulations for the crossing of complex (unsignalized) intersections. Our approach performs nearly as good as with full prior information about the intentions of the other vehicles and clearly outperforms reactive approaches.

Ensuring safety in partially-known environments is a critical problem in robotics since the environment is perceived through sensors and the environment cannot be completely known ahead of time. Prior work has considered the problem of finding positive control invariant sets (PCIS). However, this approach limits the planning horizon of the motion planner since the PCIS must lie completely in the limited known part of the environment. Here we consider the problem of guaranteeing safety by ensuring the existence of at least one PCIS in partially-known environments leading to an extension of the PCIS concept. It is shown, that this novel method is less conservative than the common PCIS approach and robust to unknown small obstacles which might appear in the close vicinity of the robot. An example implementation for loiter circles and power line obstacles is presented. Simulation scenarios are used for validating the proposed concept.

Autonomous mobile robots are required to operate in partially known and unstructured environments. It is imperative to guarantee safety of such systems for their successful deployment. Current state of the art does not fully exploit the sensor and dynamic capabilities of a robot. Also, given the non-holonomic systems with non-linear dynamic constraints, it becomes computationally infeasible to find an optimal solution if the full dynamics are to be exploited online. In this paper we present an online algorithm to guarantee the safety of the robot through an emergency maneuver library. The maneuvers in the emergency maneuver library are optimized such that the probability of finding an emergency maneuver that lies in the known obstacle free space is maximized. We prove that the related trajectory set diversity problem is monotonic and sub-modular which enables one to develop an efficient trajectory set generation algorithm with bounded sub-optimality. We generate an off-line computed trajectory set that exploits the full dynamics of the robot and the known obstacle-free region. We test and validate the algorithm on a full-size autonomous helicopter flying up to speeds of 56m/sin partially-known environments. We present results from 4 months of flight testing where the helicopter has been avoiding trees, performing autonomous landing, avoiding mountains while being guaranteed safe.

We address the problem of verifying motion plans for aerial robots in uncertain and partially-known environments. Thereby, the initial state of the robot is uncertain due to errors from the state estimation and the motion is uncertain due to wind disturbances and control errors caused by sensor noise. Since the environment is perceived at runtime, the verification of partial motion plans must be performed online (i.e. during operation) to ensure safety within the planning horizon and beyond. This is achieved by efficiently generating robust control invariant sets based on so-called loiter circles, where the position of the aerial robot follows a circular pattern. Verification of aerial robots is challenging due to the nonlinearity of their dynamics, the high dimensionality of their state space, and their potentially high velocities. We use novel techniques from reachability analysis to overcome those challenges. In order to ensure that the robot never finds itself in a situation for which no safe maneuver exists, we provide a technique that ensures safety of aerial robots beyond the planning horizon. Our method is applicable to all kinds of robotic systems that follow reference trajectories, such as bipedal robotic walking, robotic manipulators, automated vehicles, and the like. We evaluate our method by simulations of high speed helicopter flights.

In this work, a framework for motion prediction of vehicles and safety assessment of traffic scenes is presented. The developed framework can be used for driver assistant systems as well as for autonomous driving applications. In order to assess the safety of the future trajectories of the vehicle, these systems require a prediction of the future motion of all traffic participants. As the traffic participants have a mutual influence on each other, the interaction of them is explicitly considered in this framework, which is inspired by an optimization problem. Taking the mutual influence of traffic participants into account, this framework differs from the existing approaches which consider the interaction only insufficiently, suffering reliability in real traffic scenes. For motion prediction, the collision probability of a vehicle performing a certain maneuver, is computed. Based on the safety evaluation and the assumption that drivers avoid collisions, the prediction is realized. Simulation scenarios and real-world results show the functionality.

This paper presents a method for reasoning about the safety of traffic situations. More precisely, the problem of safety assessment for partial trajectories for vehicles is addressed. Therefore, the Inevitable Collision States (ICS) as well as its probabilistic generalization the Probabilistic Collision States (PCS) are used. Thereby, the assessment is performed for an infinite time horizon. For solving the ICS computation nonlinear programming is applied. In addition to the safety assessment an evaluation of the disturbance of the other traffic participants by the ego vehicle is presented. The results are integrated into an optimal control based planning approach that generates minimum jerk trajectories. An example implementation of the proposed framework is applied to simulation scenarios that demonstrates the necessity of the presented method for guaranteeing motion safety.

This paper presents a probabilistic threat assessment method for reasoning about the safety of robot trajectories in uncertain and dynamic environments. For safety evaluation, the overall collision probability is used to rank candidate trajectories by considering the collision probability of known objects as well as the collision probability beyond the planning horizon. Monte Carlo sampling is used to estimate the collision probabilities. This concept is applied to a navigation framework that generates and selects trajectories in order to reach the goal location while minimizing the collision probability. Simulation scenarios are used to validate the overall crash probability and show its necessity in the proposed navigation approach.

This work presents an extension of the Dynamic Window Approach. The reactive collision avoidance algorithm is generalized to the case of omni-directional kinematics for any polygonal shaped, mobile robot. This paper includes a superior implementation to former realizations and has already been successfully tested with an omni-directional robot. The implementation is efficient and produces collision-free trajectories even in narrow and crowded environments.

For reasoning about the safety of a robot system, it is sufficient to pretend the robot to reach an Inevitable Collision Sate (ICS). Otherwise, there exists no future trajectory which can avoid a collision. The usage of ICS is limited due to its computational complexity. One reason for this is, that the ICS computation cannot be done separately for each obstacle. Hence, ICS needs to be recomputed from scratch if another object appears in the scene. The main contribution of this paper is a modified ICS calculation which allows to compute the union of ICS sets in a sequential manner, thus reducing the computational requirements in case of new obstacles. Therefore, two novel ICS-Checker algorithms are presented reducing the computational effort. Furthermore, this novel calculation is used to reduce the probability of being in an ICS regarding an unforeseen obstacle.

For path planning algorithms of robots it is important that the robot does not reach a state of inevitable collision. In crowded environments with many humans or robots, the set of possible inevitable collision states (ICS) is often unacceptably high, such that the robot has to stop and wait in too many situations. For this reason, the concept of ICS is extended to probabilistic collision states (PCS), which estimates the collision probability for a given state. This allows to efficiently run planning algorithms through crowded environments when accepting a certain collision probability. A further novelty is that the obstacles possibly react to the robot in order to mitigate the risk of a collision. The results show a significant difference in interaction behavior. Thus, this approach is especially suited for active and non-deterministic moving obstacles in the robot workspace.

The verification of evasive maneuvers for autonomous vehicles driving with constant velocity is considered. Modeling uncertainties, uncertain measurements, and disturbances can cause substantial deviations from an initially planned evasive maneuver. From this follows that the maneuver, which is safe under perfect conditions, might become unsafe. In this work, the possible set of deviations is computed with methods from reachability analysis, which allows to verify evasive maneuvers under consideration of the mentioned uncertainties. Since the presented approach has a short response time, it can be applied for real time safety decisions. The methods are presented for a numerical example where two autonomous cars plan a coordinated evasive maneuver in order to prevent a collision with a wrong-way driver.

As mobile robotics is gradually moving towards a level of semantic environment understanding, robust 3D object recognition plays an increasingly important role. One of the most crucial prerequisites for object recognition is a set of fast algorithms for geometry segmentation and extraction, which in turn rely on surface normal vectors as a fundamental feature. Although there exists a plethora of different approaches for estimating normal vectors from 3D point clouds, it is largely unclear which methods are preferable for online processing on a mobile robot. This paper presents a detailed analysis and comparison of existing methods for surface normal estimation with a special emphasis on the trade-off between quality and speed. The study sheds light on the computational complexity as well as the qualitative differences between methods and provides guidelines on choosing the dasiarightpsila algorithm for the robotics practitioner. The robustness of the methods with respect to noise and neighborhood size is analyzed. All algorithms are benchmarked with simulated as well as real 3D laser data obtained from a mobile robot.