--Collaborative robots must quickly adapt to their partner's intent and preferences to proactively identify helpful actions. This is especially true in situated settings where human partners can continually teach robots new high-level behaviors, visual concepts, and physical skills (e.g., through demonstration), growing the robot's capabilities as the human-robot pair work together to accomplish diverse tasks. In this work, we argue that robots should be able to infer their partner's goals from early interactions and use this information to proactively plan behaviors ahead of explicit instructions from the user . Building from the strong commonsense priors and steerability of large language models, we introduce ProV ox ("Proactive V oice"), a novel framework that enables robots to efficiently personalize and adapt to individual collaborators. We design a meta-prompting protocol that empowers users to communicate their distinct preferences, intent, and expected robot behaviors ahead of starting a physical interaction. ProV ox then uses the personalized prompt to condition a proactive language model task planner that anticipates a user's intent from the current interaction context and robot capabilities to suggest helpful actions; in doing so, we alleviate user burden, minimizing the amount of time partners spend explicitly instructing and supervising the robot. We evaluate ProV ox through user studies grounded in household manipulation tasks (e.g., assembling lunch bags) that measure the efficiency of the collaboration, as well as features such as perceived helpfulness, ease of use, and reliability. Our analysis suggests that both meta-prompting and proactivity are critical, resulting in 38.7% faster task completion times and 31.9% less user burden relative to non-active baselines. Collaborative robots must be able to continually infer their partner's intent, adapting from this information to personalize and proactively suggest helpful actions.

It has been shown recently that successful techniques in classical planning, such as goal-oriented heuristics and landmarks, can improve the ability to compute planning programs for generalized planning (GP) problems. In this work, we introduce the notion of action novelty rank, which computes novelty with respect to a planning program, and propose novelty-based generalized planning solvers, which prune a newly generated planning program if its most frequent action repetition is greater than a given bound $v$, implemented by novelty-based best-first search BFS($v$) and its progressive variant PGP($v$). Besides, we introduce lifted helpful actions in GP derived from action schemes, and propose new evaluation functions and structural program restrictions to scale up the search. Our experiments show that the new algorithms BFS($v$) and PGP($v$) outperform the state-of-the-art in GP over the standard generalized planning benchmarks. Practical findings on the above-mentioned methods in generalized planning are briefly discussed.

It is known that seemingly small details such as tie-breaking among nodes with the same f-cost can significantly affect the performance of a best-first search algorithm on many domains (Asai and Fukunaga 2017). In this paper, we show that low-level algorithmic details of domain-independent planning heuristics can have a surprisingly large impact on search performance. As a case study, we consider the well-known FF heuristic (hff ) (Hoffmann and Nebel 2001).

We describe and evaluate the algorithmic techniques that are used in the FF planning system. Like the HSP system, FF relies on forward state space search, using a heuristic that estimates goal distances by ignoring delete lists. Unlike HSP's heuristic, our method does not assume facts to be independent. We introduce a novel search strategy that combines hill-climbing with systematic search, and we show how other powerful heuristic information can be extracted and used to prune the search space. FF was the most successful automatic planner at the recent AIPS-2000 planning competition. We review the results of the competition, give data for other benchmark domains, and investigate the reasons for the runtime performance of FF compared to HSP.

We define a probe to be a single action sequence computedgreedily from a given state that either terminates in the goalor fails. We show that by designing these probes carefullyusing a number of existing and new polynomial techniquessuch as helpful actions, landmarks, commitments, and con-sistent subgoals, a single probe from the initial state solvesby itself 683 out of 980 problems from previous IPCs, a num-ber that compares well with the 627 problems solved by FFin EHC mode, with similar times and plan lengths. We alsoshow that by launching one probe from each expanded statein a standard greedy best first search informed by the addi-tive heuristic, the number of problems solved jumps to 900(92%), as opposed to FF that solves 827 problems (84%),and LAMA that solves 879 (89%). The success of probessuggests that many domains can be solved easily once a suit-able serialization of the landmarks is found, an observationthat may open new connections between recent work in plan-ning and more classical work concerning goal serializationand problem decomposition in planning and search.

Current evaluation functions for heuristic planning are expensive to compute. In numerous planning problems these functions provide good guidance to the solution, so they are worth the expense. However, when evaluation functions are misguiding or when planning problems are large enough, lots of node evaluations must be computed, which severely limits the scalability of heuristic planners. In this paper, we present a novel solution for reducing node evaluations in heuristic planning based on machine learning. Particularly, we define the task of learning search control for heuristic planning as a relational classification task, and we use an off-the-shelf relational classification tool to address this learning task. Our relational classification task captures the preferred action to select in the different planning contexts of a specific planning domain. These planning contexts are defined by the set of helpful actions of the current state, the goals remaining to be achieved, and the static predicates of the planning task. This paper shows two methods for guiding the search of a heuristic planner with the learned classifiers. The first one consists of using the resulting classifier as an action policy. The second one consists of applying the classifier to generate lookahead states within a Best First Search algorithm. Experiments over a variety of domains reveal that our heuristic planner using the learned classifiers solves larger problems than state-of-the-art planners.

We present a planning domain that encodes the problem of generating natural language sentences. This domain has a number of features that provoke fairly unusual behavior in planners. In particular, hitherto no existing automated planner was sufficiently effective to be of practical value in this application. We analyze in detail the reasons for ineffectiveness in FF, resulting in a few minor implementation fixes in FF's preprocessor, and in a basic reconfiguration of its search options. The performance of the modified FF is up to several orders of magnitude better than that of the original FF, and for the first time makes automated planners a practical possibility for this application. Beside thus highlighting the importance of preprocessing and automated configuration techniques, we show that the domain still poses several interesting challenges to the development of search heuristics.

Forward State Planning with Reachability Heuristics is arguably the most successful approach to Automated Planning up to date. In addition to an estimation of the distance to the goal, relaxed plans obtained with such heuristics provide the search with useful information such as helpful actions and look-ahead states. However, this information is extracted only from the beginning of the relaxed plan. In this paper, we propose using information extracted from the last actions in the relaxed plan to generate intermediate goals backwards. This allows us to use information from previous computations of the heuristic and reduce the depth of the search tree.

N-gram analysis provides a means of probabilistically predicting the next item in a sequence. Due originally to Shannon, it has proven an effective technique for word prediction in natural language processing and for gene sequence analysis. In this paper, we investigate the utility of n-gram analysis in predicting operator sequences in plans. Given a set of sample plans, we perform n-gram analysis to predict the likelihood of subsequent operators, relative to a partial plan. We identify several ways in which this information might be integrated into a planner. In this paper, we investigate one of these directions in further detail. Preliminary results demonstrate the promise of n-gram analysis as a tool for improving planning performance.

Heuristic forward search is the dominant approach to satisficing planning to date. Most successful planning systems, however, go beyond plain heuristic search by employing various search-enhancement techniques.  One example is the use of helpful actions or preferred operators, providing information which may complement heuristic values.  A second example is deferred heuristic evaluation, a search variant which can reduce the number of costly node evaluations. Despite the wide-spread use of these search-enhancement techniques however, we note that few results have been published examining their usefulness. In particular, while various ways of using, and possibly combining, these techniques are conceivable, no work to date has studied the performance of such variations.  In this paper, we address this gap by examining the use of preferred operators and deferred evaluation in a variety of settings within best-first search. In particular, our findings are consistent with and help explain the good performance of the winners of the satisficing tracks at IPC 2004 and 2008.